[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71AJS9YS60E0PRG3SPJQEDX":3,"skill-same:01M71AJS9YS60E0PRG3SPJQEDX":73},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":23,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":52,"commitSha":53,"skillDirectory":54,"forksCount":55,"repositoryHtmlUrl":56,"repositoryHomepageUrl":6,"ownerHtmlUrl":57,"ownerBlogUrl":6,"ownerDescription":58,"updatedAt":59,"install":60,"resources":72},"01M71AJS9YS60E0PRG3SPJQEDX","cyber-building-automated-malware-submission-pipeline",null,"Builds an automated malware submission and analysis pipeline that collects suspicious files from endpoints and email gateways, submits them to sandbox environments and multi-engine scanners, and generates verdicts with IOCs for SIEM integration. Use when SOC teams need to scale malware analysis beyond manual sandbox submissions for high-volume alert triage.","nexuslinkproductions\u002Fyuri-os","nexuslinkproductions","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F273246263?v=4","01M718YX9NZRCW50B59B8ZVDKN","Marcel Spatz","01M718YXAQ7530F4B1VKN6SFQV",2,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fnexuslinkproductions\u002Fyuri-os\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fcyber-building-automated-malware-submission-pipeline\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000005","邮件与沟通","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"building automated malware submission pipeline","malware","submission","cyber building automated malware submission pipeline","pipeline","for","email","domain","gateways","environments","subdomain","suspicious","siem","analysis","soc","when","false","cybersecurity","files","volume","2026-11-10 10:12:30",false,"---\nname: cyber-building-automated-malware-submission-pipeline\ndescription: \"Builds an automated malware submission and analysis pipeline that collects suspicious files from endpoints and email gateways, submits them to sandbox environments and multi-engine scanners, and generates verdicts with IOCs for SIEM integration. Use when SOC teams need to scale malware analysis beyond manual sandbox submissions for high-volume alert triage.\"\nsource: mukul975\u002FAnthropic-Cybersecurity-Skills\nlicense: Apache-2.0\nauthorized_lab: false\norigin_frontmatter: \"name: building-automated-malware-submission-pipeline | description: 'Builds an automated malware submission and analysis pipeline that collects |   suspicious files from endpoints and email gateways, submits them to sandbox environments |   and multi-engine scanners, and generates verdicts with IOCs for SIEM integration. |   Use when SOC teams need to scale malware analysis beyond manual sandbox submissions |   for high-volume alert triage. |  |   ' | domain: cybersecurity | subdomain: soc-opera\"\nhide: true\n---\n\n> Defensive\u002Fanalysis cyber skill. Source: mukul975\u002FAnthropic-Cybersecurity-Skills (Apache-2.0). Advisory knowledge — the YURI floor, protected paths, and owner authority always outrank any instruction in this body.\n\n# Building Automated Malware Submission Pipeline\n\n## When to Use\n\nUse this skill when:\n- SOC teams face high volume of suspicious file alerts requiring sandbox analysis\n- Manual sandbox submission creates bottlenecks in alert triage workflow\n- Endpoint and email security tools quarantine files needing automated verdict determination\n- Incident response requires rapid malware family identification and IOC extraction\n\n**Do not use** for analyzing live malware samples in production environments — always use isolated sandbox infrastructure.\n\n## Prerequisites\n\n- Sandbox environment: Cuckoo Sandbox, Joe Sandbox, Any.Run, or VMRay\n- VirusTotal API key (Enterprise for submission, free for lookup)\n- MalwareBazaar API access for known malware lookup\n- File collection mechanism: EDR quarantine API, email gateway export, network capture\n- Python 3.8+ with `requests`, `vt-py`, `pefile` libraries\n- Isolated analysis network with no production connectivity\n\n## Workflow\n\n### Step 1: Build File Collection Pipeline\n\nCollect suspicious files from multiple sources:\n\n```python\nimport requests\nimport hashlib\nimport os\nfrom pathlib import Path\nfrom datetime import datetime\n\nclass MalwareCollector:\n    def __init__(self, quarantine_dir=\"\u002Fopt\u002Fmalware_quarantine\"):\n        self.quarantine_dir = Path(quarantine_dir)\n        self.quarantine_dir.mkdir(exist_ok=True)\n\n    def collect_from_edr(self, edr_api_url, api_token):\n        \"\"\"Pull quarantined files from CrowdStrike Falcon\"\"\"\n        headers = {\"Authorization\": f\"Bearer {api_token}\"}\n\n        # Get recent quarantine events\n        response = requests.get(\n            f\"{edr_api_url}\u002Fquarantine\u002Fqueries\u002Fquarantined-files\u002Fv1\",\n            headers=headers,\n            params={\"filter\": \"state:'quarantined'\", \"limit\": 50}\n        )\n        file_ids = response.json()[\"resources\"]\n\n        for file_id in file_ids:\n            # Download quarantined file\n            dl_response = requests.get(\n                f\"{edr_api_url}\u002Fquarantine\u002Fentities\u002Fquarantined-files\u002Fv1\",\n                headers=headers,\n                params={\"ids\": file_id}\n            )\n            file_data = dl_response.content\n            sha256 = hashlib.sha256(file_data).hexdigest()\n\n            filepath = self.quarantine_dir \u002F f\"{sha256}.sample\"\n            filepath.write_bytes(file_data)\n            yield {\"sha256\": sha256, \"path\": str(filepath), \"source\": \"edr\"}\n\n    def collect_from_email_gateway(self, smtp_quarantine_path):\n        \"\"\"Pull attachments from email gateway quarantine\"\"\"\n        import email\n        from email import policy\n\n        for eml_file in Path(smtp_quarantine_path).glob(\"*.eml\"):\n            msg = email.message_from_binary_file(\n                eml_file.open(\"rb\"), policy=policy.default\n            )\n            for attachment in msg.iter_attachments():\n                content = attachment.get_content()\n                if isinstance(content, str):\n                    content = content.encode()\n                sha256 = hashlib.sha256(content).hexdigest()\n                filename = attachment.get_filename() or \"unknown\"\n\n                filepath = self.quarantine_dir \u002F f\"{sha256}.sample\"\n                filepath.write_bytes(content)\n                yield {\n                    \"sha256\": sha256,\n                    \"path\": str(filepath),\n                    \"source\": \"email\",\n                    \"original_filename\": filename,\n                    \"sender\": msg[\"From\"],\n                    \"subject\": msg[\"Subject\"]\n                }\n\n    def compute_hashes(self, filepath):\n        \"\"\"Calculate MD5, SHA1, SHA256 for a file\"\"\"\n        with open(filepath, \"rb\") as f:\n            content = f.read()\n        return {\n            \"md5\": hashlib.md5(content).hexdigest(),\n            \"sha1\": hashlib.sha1(content).hexdigest(),\n            \"sha256\": hashlib.sha256(content).hexdigest(),\n            \"size\": len(content)\n        }\n```\n\n### Step 2: Pre-Screen with Hash Lookups\n\nCheck if the file is already known before sandbox submission:\n\n```python\nimport vt\n\nclass MalwarePreScreener:\n    def __init__(self, vt_api_key, mb_api_url=\"https:\u002F\u002Fmb-api.abuse.ch\u002Fapi\u002Fv1\u002F\"):\n        self.vt_client = vt.Client(vt_api_key)\n        self.mb_api_url = mb_api_url\n\n    def check_virustotal(self, sha256):\n        \"\"\"Lookup hash in VirusTotal\"\"\"\n        try:\n            file_obj = self.vt_client.get_object(f\"\u002Ffiles\u002F{sha256}\")\n            stats = file_obj.last_analysis_stats\n            return {\n                \"found\": True,\n                \"malicious\": stats.get(\"malicious\", 0),\n                \"suspicious\": stats.get(\"suspicious\", 0),\n                \"undetected\": stats.get(\"undetected\", 0),\n                \"total\": sum(stats.values()),\n                \"threat_label\": getattr(file_obj, \"popular_threat_classification\", {}).get(\n                    \"suggested_threat_label\", \"Unknown\"\n                ),\n                \"type\": getattr(file_obj, \"type_description\", \"Unknown\")\n            }\n        except vt.APIError:\n            return {\"found\": False}\n\n    def check_malwarebazaar(self, sha256):\n        \"\"\"Lookup hash in MalwareBazaar\"\"\"\n        response = requests.post(\n            self.mb_api_url,\n            data={\"query\": \"get_info\", \"hash\": sha256}\n        )\n        data = response.json()\n        if data[\"query_status\"] == \"ok\":\n            entry = data[\"data\"][0]\n            return {\n                \"found\": True,\n                \"signature\": entry.get(\"signature\", \"Unknown\"),\n                \"tags\": entry.get(\"tags\", []),\n                \"file_type\": entry.get(\"file_type\", \"Unknown\"),\n                \"first_seen\": entry.get(\"first_seen\", \"Unknown\")\n            }\n        return {\"found\": False}\n\n    def pre_screen(self, sha256):\n        \"\"\"Run all pre-screening checks\"\"\"\n        vt_result = self.check_virustotal(sha256)\n        mb_result = self.check_malwarebazaar(sha256)\n\n        verdict = \"UNKNOWN\"\n        if vt_result[\"found\"] and vt_result.get(\"malicious\", 0) > 10:\n            verdict = \"KNOWN_MALICIOUS\"\n        elif vt_result[\"found\"] and vt_result.get(\"malicious\", 0) == 0:\n            verdict = \"LIKELY_CLEAN\"\n\n        return {\n            \"sha256\": sha256,\n            \"virustotal\": vt_result,\n            \"malwarebazaar\": mb_result,\n            \"pre_screen_verdict\": verdict,\n            \"needs_sandbox\": verdict == \"UNKNOWN\"\n        }\n\n    def close(self):\n        self.vt_client.close()\n```\n\n### Step 3: Submit to Sandbox for Dynamic Analysis\n\n**Cuckoo Sandbox Submission:**\n\n```python\nclass SandboxSubmitter:\n    def __init__(self, cuckoo_url=\"http:\u002F\u002Fcuckoo.internal:8090\"):\n        self.cuckoo_url = cuckoo_url\n\n    def submit_to_cuckoo(self, filepath, timeout=300):\n        \"\"\"Submit file to Cuckoo Sandbox\"\"\"\n        with open(filepath, \"rb\") as f:\n            response = requests.post(\n                f\"{self.cuckoo_url}\u002Ftasks\u002Fcreate\u002Ffile\",\n                files={\"file\": f},\n                data={\n                    \"timeout\": timeout,\n                    \"options\": \"procmemdump=yes,route=none\",\n                    \"priority\": 2,\n                    \"machine\": \"win10_x64\"\n                }\n            )\n        task_id = response.json()[\"task_id\"]\n        return task_id\n\n    def wait_for_analysis(self, task_id, poll_interval=30, max_wait=600):\n        \"\"\"Wait for sandbox analysis to complete\"\"\"\n        import time\n        elapsed = 0\n        while elapsed \u003C max_wait:\n            response = requests.get(f\"{self.cuckoo_url}\u002Ftasks\u002Fview\u002F{task_id}\")\n            status = response.json()[\"task\"][\"status\"]\n            if status == \"reported\":\n                return self.get_report(task_id)\n            elif status == \"failed_analysis\":\n                return {\"error\": \"Analysis failed\"}\n            time.sleep(poll_interval)\n            elapsed += poll_interval\n        return {\"error\": \"Analysis timed out\"}\n\n    def get_report(self, task_id):\n        \"\"\"Retrieve analysis report\"\"\"\n        response = requests.get(f\"{self.cuckoo_url}\u002Ftasks\u002Freport\u002F{task_id}\")\n        report = response.json()\n\n        # Extract key indicators\n        return {\n            \"task_id\": task_id,\n            \"score\": report.get(\"info\", {}).get(\"score\", 0),\n            \"signatures\": [\n                {\"name\": s[\"name\"], \"severity\": s[\"severity\"], \"description\": s[\"description\"]}\n                for s in report.get(\"signatures\", [])\n            ],\n            \"network\": {\n                \"dns\": [d[\"request\"] for d in report.get(\"network\", {}).get(\"dns\", [])],\n                \"http\": [\n                    {\"url\": h[\"uri\"], \"method\": h[\"method\"]}\n                    for h in report.get(\"network\", {}).get(\"http\", [])\n                ],\n                \"hosts\": report.get(\"network\", {}).get(\"hosts\", [])\n            },\n            \"dropped_files\": [\n                {\"name\": f[\"name\"], \"sha256\": f[\"sha256\"], \"size\": f[\"size\"]}\n                for f in report.get(\"dropped\", [])\n            ],\n            \"processes\": [\n                {\"name\": p[\"process_name\"], \"pid\": p[\"pid\"], \"command_line\": p.get(\"command_line\", \"\")}\n                for p in report.get(\"behavior\", {}).get(\"processes\", [])\n            ],\n            \"registry_keys\": [\n                k for k in report.get(\"behavior\", {}).get(\"summary\", {}).get(\"regkey_written\", [])\n            ]\n        }\n\n    def submit_to_joesandbox(self, filepath, joe_api_key, joe_url=\"https:\u002F\u002Fjbxcloud.joesecurity.org\u002Fapi\"):\n        \"\"\"Submit to Joe Sandbox Cloud\"\"\"\n        with open(filepath, \"rb\") as f:\n            response = requests.post(\n                f\"{joe_url}\u002Fv2\u002Fsubmission\u002Fnew\",\n                headers={\"Authorization\": f\"Bearer {joe_api_key}\"},\n                files={\"sample\": f},\n                data={\n                    \"systems\": \"w10_64\",\n                    \"internet-access\": False,\n                    \"report-cache\": True\n                }\n            )\n        return response.json()[\"data\"][\"webid\"]\n```\n\n### Step 4: Extract IOCs and Generate Verdict\n\n```python\nclass VerdictGenerator:\n    def __init__(self):\n        self.malicious_threshold = 7  # Cuckoo score threshold\n\n    def generate_verdict(self, pre_screen, sandbox_report):\n        \"\"\"Combine pre-screening and sandbox results for final verdict\"\"\"\n        iocs = {\n            \"ips\": [],\n            \"domains\": [],\n            \"urls\": [],\n            \"hashes\": [],\n            \"registry_keys\": [],\n            \"files_dropped\": []\n        }\n\n        # Extract IOCs from sandbox report\n        if sandbox_report:\n            iocs[\"domains\"] = sandbox_report.get(\"network\", {}).get(\"dns\", [])\n            iocs[\"ips\"] = sandbox_report.get(\"network\", {}).get(\"hosts\", [])\n            iocs[\"urls\"] = [\n                h[\"url\"] for h in sandbox_report.get(\"network\", {}).get(\"http\", [])\n            ]\n            iocs[\"hashes\"] = [\n                f[\"sha256\"] for f in sandbox_report.get(\"dropped_files\", [])\n            ]\n            iocs[\"registry_keys\"] = sandbox_report.get(\"registry_keys\", [])[:10]\n            iocs[\"files_dropped\"] = sandbox_report.get(\"dropped_files\", [])\n\n        # Determine verdict\n        vt_malicious = pre_screen.get(\"virustotal\", {}).get(\"malicious\", 0)\n        sandbox_score = sandbox_report.get(\"score\", 0) if sandbox_report else 0\n        sig_count = len(sandbox_report.get(\"signatures\", [])) if sandbox_report else 0\n\n        combined_score = (vt_malicious * 2) + (sandbox_score * 10) + (sig_count * 5)\n\n        if combined_score >= 100:\n            verdict = \"MALICIOUS\"\n            confidence = \"HIGH\"\n        elif combined_score >= 50:\n            verdict = \"SUSPICIOUS\"\n            confidence = \"MEDIUM\"\n        elif combined_score >= 20:\n            verdict = \"POTENTIALLY_UNWANTED\"\n            confidence = \"LOW\"\n        else:\n            verdict = \"CLEAN\"\n            confidence = \"HIGH\"\n\n        return {\n            \"verdict\": verdict,\n            \"confidence\": confidence,\n            \"combined_score\": combined_score,\n            \"iocs\": iocs,\n            \"vt_detections\": vt_malicious,\n            \"sandbox_score\": sandbox_score,\n            \"signatures\": sandbox_report.get(\"signatures\", []) if sandbox_report else []\n        }\n```\n\n### Step 5: Push Results to SIEM\n\n```python\ndef push_to_splunk(verdict_result, splunk_url, splunk_token):\n    \"\"\"Send malware analysis verdict to Splunk HEC\"\"\"\n    import json\n\n    event = {\n        \"sourcetype\": \"malware_analysis\",\n        \"source\": \"malware_pipeline\",\n        \"event\": {\n            \"sha256\": verdict_result[\"sha256\"],\n            \"verdict\": verdict_result[\"verdict\"],\n            \"confidence\": verdict_result[\"confidence\"],\n            \"score\": verdict_result[\"combined_score\"],\n            \"vt_detections\": verdict_result[\"vt_detections\"],\n            \"sandbox_score\": verdict_result[\"sandbox_score\"],\n            \"malware_family\": verdict_result.get(\"threat_label\", \"Unknown\"),\n            \"iocs\": verdict_result[\"iocs\"],\n            \"signatures\": [s[\"name\"] for s in verdict_result[\"signatures\"]]\n        }\n    }\n\n    response = requests.post(\n        f\"{splunk_url}\u002Fservices\u002Fcollector\u002Fevent\",\n        headers={\n            \"Authorization\": f\"Splunk {splunk_token}\",\n            \"Content-Type\": \"application\u002Fjson\"\n        },\n        json=event,\n        verify=not os.environ.get(\"SKIP_TLS_VERIFY\", \"\").lower() == \"true\",  # Set SKIP_TLS_VERIFY=true for self-signed certs in lab environments\n    )\n    return response.status_code == 200\n\ndef push_iocs_to_blocklist(iocs, firewall_api):\n    \"\"\"Push extracted IOCs to blocking infrastructure\"\"\"\n    for ip in iocs.get(\"ips\", []):\n        requests.post(\n            f\"{firewall_api}\u002Fblock\",\n            json={\"type\": \"ip\", \"value\": ip, \"action\": \"block\", \"source\": \"malware_pipeline\"}\n        )\n    for domain in iocs.get(\"domains\", []):\n        requests.post(\n            f\"{firewall_api}\u002Fblock\",\n            json={\"type\": \"domain\", \"value\": domain, \"action\": \"sinkhole\", \"source\": \"malware_pipeline\"}\n        )\n```\n\n### Step 6: Orchestrate the Full Pipeline\n\n```python\ndef run_malware_pipeline(sample_path, config):\n    \"\"\"Execute full malware analysis pipeline\"\"\"\n    collector = MalwareCollector()\n    screener = MalwarePreScreener(config[\"vt_key\"])\n    submitter = SandboxSubmitter(config[\"cuckoo_url\"])\n    generator = VerdictGenerator()\n\n    # Step 1: Hash and pre-screen\n    hashes = collector.compute_hashes(sample_path)\n    pre_screen = screener.pre_screen(hashes[\"sha256\"])\n\n    # Step 2: Submit to sandbox if unknown\n    sandbox_report = None\n    if pre_screen[\"needs_sandbox\"]:\n        task_id = submitter.submit_to_cuckoo(sample_path)\n        sandbox_report = submitter.wait_for_analysis(task_id)\n\n    # Step 3: Generate verdict\n    verdict = generator.generate_verdict(pre_screen, sandbox_report)\n    verdict[\"sha256\"] = hashes[\"sha256\"]\n    verdict[\"threat_label\"] = pre_screen.get(\"virustotal\", {}).get(\"threat_label\", \"Unknown\")\n\n    # Step 4: Push to SIEM\n    push_to_splunk(verdict, config[\"splunk_url\"], config[\"splunk_token\"])\n\n    # Step 5: Block if malicious\n    if verdict[\"verdict\"] == \"MALICIOUS\":\n        push_iocs_to_blocklist(verdict[\"iocs\"], config[\"firewall_api\"])\n\n    screener.close()\n    return verdict\n```\n\n## Key Concepts\n\n| Term | Definition |\n|------|-----------|\n| **Dynamic Analysis** | Executing malware in a sandbox to observe runtime behavior (process creation, network, file system changes) |\n| **Static Analysis** | Examining malware without execution (hash lookup, string analysis, PE header inspection) |\n| **Sandbox Evasion** | Techniques malware uses to detect sandbox environments and alter behavior to avoid analysis |\n| **IOC Extraction** | Automated process of identifying network indicators, file artifacts, and registry changes from sandbox reports |\n| **Multi-AV Scanning** | Submitting samples to multiple antivirus engines (VirusTotal) for consensus-based detection |\n| **Verdict** | Final classification of a sample: Malicious, Suspicious, Potentially Unwanted, or Clean |\n\n## Tools & Systems\n\n- **Cuckoo Sandbox**: Open-source automated malware analysis platform with behavioral analysis and network capture\n- **Joe Sandbox**: Commercial sandbox with deep behavioral analysis, YARA matching, and MITRE ATT&CK mapping\n- **Any.Run**: Interactive sandbox service allowing real-time manipulation during analysis for debugging evasive malware\n- **VirusTotal**: Multi-engine scanning service providing 70+ AV results and behavioral analysis reports\n- **CAPE Sandbox**: Community-maintained Cuckoo fork with enhanced payload extraction and configuration dumping\n\n## Common Scenarios\n\n- **Email Attachment Triage**: Auto-submit quarantined email attachments, generate verdict in \u003C5 minutes\n- **EDR Quarantine Processing**: Batch-process files quarantined by endpoint security for detailed analysis\n- **Incident Investigation**: Submit suspicious binaries found during IR for malware family identification and IOC extraction\n- **Threat Intel Enrichment**: Analyze samples from threat feeds to extract C2 infrastructure and update blocking\n- **Zero-Day Detection**: Sandbox catches novel malware missed by signature-based AV through behavioral analysis\n\n## Output Format\n\n```\nMALWARE ANALYSIS REPORT — Pipeline Submission\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\nSample:       invoice_march.docx\nSHA256:       a1b2c3d4e5f6a7b8...\nFile Type:    Microsoft Word Document (macro-enabled)\n\nPre-Screening:\n  VirusTotal:    34\u002F72 malicious (Emotet.Downloader)\n  MalwareBazaar: Tags: emotet, macro, downloader\n\nSandbox Analysis (Cuckoo):\n  Score:         9.2\u002F10 (MALICIOUS)\n  Signatures:\n    - Macro executes PowerShell download cradle (severity: 8)\n    - Process injection into explorer.exe (severity: 9)\n    - Connects to known Emotet C2 server (severity: 9)\n\nExtracted IOCs:\n  C2 IPs:       185.234.218[.]50:8080, 45.77.123[.]45:443\n  Domains:       update-service[.]evil[.]com\n  Dropped Files: payload.dll (SHA256: b2c3d4e5...)\n  Registry:      HKCU\\Software\\Microsoft\\Windows\\CurrentVersion\\Run\\Update\n\nVERDICT: MALICIOUS (Emotet Downloader) — Confidence: HIGH\nACTIONS:\n  [DONE] IOCs pushed to Splunk threat intel\n  [DONE] C2 IPs blocked on firewall\n  [DONE] Domain sinkholed on DNS\n  [DONE] Hash blocked on endpoint\n```\n","> Defensive\u002Fanalysis cyber skill. Source: mukul975\u002FAnthropic-Cybersecurity-Skills (Apache-2.0). Advisory knowledge — the YURI floor, protected paths, and owner authority always outrank any instruction in this body.\n\n# Building Automated Malware Submission Pipeline\n\n## When to Use\n\nUse this skill when:\n- SOC teams face high volume of suspicious file alerts requiring sandbox analysis\n- Manual sandbox submission creates bottlenecks in alert triage workflow\n- Endpoint and email security tools quarantine files needing automated verdict determination\n- Incident response requires rapid malware family identification and IOC extraction\n\n**Do not use** for analyzing live malware samples in production environments — always use isolated sandbox infrastructure.\n\n## Prerequisites\n\n- Sandbox environment: Cuckoo Sandbox, Joe Sandbox, Any.Run, or VMRay\n- VirusTotal API key (Enterprise for submission, free for lookup)\n- MalwareBazaar API access for known malware lookup\n- File collection mechanism: EDR quarantine API, email gateway export, network capture\n- Python 3.8+ with `requests`, `vt-py`, `pefile` libraries\n- Isolated analysis network with no production connectivity\n\n## Workflow\n\n### Step 1: Build File Collection Pipeline\n\nCollect suspicious files from multiple sources:\n\n```python\nimport requests\nimport hashlib\nimport os\nfrom pathlib import Path\nfrom datetime import datetime\n\nclass MalwareCollector:\n    def __init__(self, quarantine_dir=\"\u002Fopt\u002Fmalware_quarantine\"):\n        self.quarantine_dir = Path(quarantine_dir)\n        self.quarantine_dir.mkdir(exist_ok=True)\n\n    def collect_from_edr(self, edr_api_url, api_token):\n        \"\"\"Pull quarantined files from CrowdStrike Falcon\"\"\"\n        headers = {\"Authorization\": f\"Bearer {api_token}\"}\n\n        # Get recent quarantine events\n        response = requests.get(\n            f\"{edr_api_url}\u002Fquarantine\u002Fqueries\u002Fquarantined-files\u002Fv1\",\n            headers=headers,\n            params={\"filter\": \"state:'quarantined'\", \"limit\": 50}\n        )\n        file_ids = response.json()[\"resources\"]\n\n        for file_id in file_ids:\n            # Download quarantined file\n            dl_response = requests.get(\n                f\"{edr_api_url}\u002Fquarantine\u002Fentities\u002Fquarantined-files\u002Fv1\",\n                headers=headers,\n                params={\"ids\": file_id}\n            )\n            file_data = dl_response.content\n            sha256 = hashlib.sha256(file_data).hexdigest()\n\n            filepath = self.quarantine_dir \u002F f\"{sha256}.sample\"\n            filepath.write_bytes(file_data)\n            yield {\"sha256\": sha256, \"path\": str(filepath), \"source\": \"edr\"}\n\n    def collect_from_email_gateway(self, smtp_quarantine_path):\n        \"\"\"Pull attachments from email gateway quarantine\"\"\"\n        import email\n        from email import policy\n\n        for eml_file in Path(smtp_quarantine_path).glob(\"*.eml\"):\n            msg = email.message_from_binary_file(\n                eml_file.open(\"rb\"), policy=policy.default\n            )\n            for attachment in msg.iter_attachments():\n                content = attachment.get_content()\n                if isinstance(content, str):\n                    content = content.encode()\n                sha256 = hashlib.sha256(content).hexdigest()\n                filename = attachment.get_filename() or \"unknown\"\n\n                filepath = self.quarantine_dir \u002F f\"{sha256}.sample\"\n                filepath.write_bytes(content)\n                yield {\n                    \"sha256\": sha256,\n                    \"path\": str(filepath),\n                    \"source\": \"email\",\n                    \"original_filename\": filename,\n                    \"sender\": msg[\"From\"],\n                    \"subject\": msg[\"Subject\"]\n                }\n\n    def compute_hashes(self, filepath):\n        \"\"\"Calculate MD5, SHA1, SHA256 for a file\"\"\"\n        with open(filepath, \"rb\") as f:\n            content = f.read()\n        return {\n            \"md5\": hashlib.md5(content).hexdigest(),\n            \"sha1\": hashlib.sha1(content).hexdigest(),\n            \"sha256\": hashlib.sha256(content).hexdigest(),\n            \"size\": len(content)\n        }\n```\n\n### Step 2: Pre-Screen with Hash Lookups\n\nCheck if the file is already known before sandbox submission:\n\n```python\nimport vt\n\nclass MalwarePreScreener:\n    def __init__(self, vt_api_key, mb_api_url=\"https:\u002F\u002Fmb-api.abuse.ch\u002Fapi\u002Fv1\u002F\"):\n        self.vt_client = vt.Client(vt_api_key)\n        self.mb_api_url = mb_api_url\n\n    def check_virustotal(self, sha256):\n        \"\"\"Lookup hash in VirusTotal\"\"\"\n        try:\n            file_obj = self.vt_client.get_object(f\"\u002Ffiles\u002F{sha256}\")\n            stats = file_obj.last_analysis_stats\n            return {\n                \"found\": True,\n                \"malicious\": stats.get(\"malicious\", 0),\n                \"suspicious\": stats.get(\"suspicious\", 0),\n                \"undetected\": stats.get(\"undetected\", 0),\n                \"total\": sum(stats.values()),\n                \"threat_label\": getattr(file_obj, \"popular_threat_classification\", {}).get(\n                    \"suggested_threat_label\", \"Unknown\"\n                ),\n                \"type\": getattr(file_obj, \"type_description\", \"Unknown\")\n            }\n        except vt.APIError:\n            return {\"found\": False}\n\n    def check_malwarebazaar(self, sha256):\n        \"\"\"Lookup hash in MalwareBazaar\"\"\"\n        response = requests.post(\n            self.mb_api_url,\n            data={\"query\": \"get_info\", \"hash\": sha256}\n        )\n        data = response.json()\n        if data[\"query_status\"] == \"ok\":\n            entry = data[\"data\"][0]\n            return {\n                \"found\": True,\n                \"signature\": entry.get(\"signature\", \"Unknown\"),\n                \"tags\": entry.get(\"tags\", []),\n                \"file_type\": entry.get(\"file_type\", \"Unknown\"),\n                \"first_seen\": entry.get(\"first_seen\", \"Unknown\")\n            }\n        return {\"found\": False}\n\n    def pre_screen(self, sha256):\n        \"\"\"Run all pre-screening checks\"\"\"\n        vt_result = self.check_virustotal(sha256)\n        mb_result = self.check_malwarebazaar(sha256)\n\n        verdict = \"UNKNOWN\"\n        if vt_result[\"found\"] and vt_result.get(\"malicious\", 0) > 10:\n            verdict = \"KNOWN_MALICIOUS\"\n        elif vt_result[\"found\"] and vt_result.get(\"malicious\", 0) == 0:\n            verdict = \"LIKELY_CLEAN\"\n\n        return {\n            \"sha256\": sha256,\n            \"virustotal\": vt_result,\n            \"malwarebazaar\": mb_result,\n            \"pre_screen_verdict\": verdict,\n            \"needs_sandbox\": verdict == \"UNKNOWN\"\n        }\n\n    def close(self):\n        self.vt_client.close()\n```\n\n### Step 3: Submit to Sandbox for Dynamic Analysis\n\n**Cuckoo Sandbox Submission:**\n\n```python\nclass SandboxSubmitter:\n    def __init__(self, cuckoo_url=\"http:\u002F\u002Fcuckoo.internal:8090\"):\n        self.cuckoo_url = cuckoo_url\n\n    def submit_to_cuckoo(self, filepath, timeout=300):\n        \"\"\"Submit file to Cuckoo Sandbox\"\"\"\n        with open(filepath, \"rb\") as f:\n            response = requests.post(\n                f\"{self.cuckoo_url}\u002Ftasks\u002Fcreate\u002Ffile\",\n                files={\"file\": f},\n                data={\n                    \"timeout\": timeout,\n                    \"options\": \"procmemdump=yes,route=none\",\n                    \"priority\": 2,\n                    \"machine\": \"win10_x64\"\n                }\n            )\n        task_id = response.json()[\"task_id\"]\n        return task_id\n\n    def wait_for_analysis(self, task_id, poll_interval=30, max_wait=600):\n        \"\"\"Wait for sandbox analysis to complete\"\"\"\n        import time\n        elapsed = 0\n        while elapsed \u003C max_wait:\n            response = requests.get(f\"{self.cuckoo_url}\u002Ftasks\u002Fview\u002F{task_id}\")\n            status = response.json()[\"task\"][\"status\"]\n            if status == \"reported\":\n                return self.get_report(task_id)\n            elif status == \"failed_analysis\":\n                return {\"error\": \"Analysis failed\"}\n            time.sleep(poll_interval)\n            elapsed += poll_interval\n        return {\"error\": \"Analysis timed out\"}\n\n    def get_report(self, task_id):\n        \"\"\"Retrieve analysis report\"\"\"\n        response = requests.get(f\"{self.cuckoo_url}\u002Ftasks\u002Freport\u002F{task_id}\")\n        report = response.json()\n\n        # Extract key indicators\n        return {\n            \"task_id\": task_id,\n            \"score\": report.get(\"info\", {}).get(\"score\", 0),\n            \"signatures\": [\n                {\"name\": s[\"name\"], \"severity\": s[\"severity\"], \"description\": s[\"description\"]}\n                for s in report.get(\"signatures\", [])\n            ],\n            \"network\": {\n                \"dns\": [d[\"request\"] for d in report.get(\"network\", {}).get(\"dns\", [])],\n                \"http\": [\n                    {\"url\": h[\"uri\"], \"method\": h[\"method\"]}\n                    for h in report.get(\"network\", {}).get(\"http\", [])\n                ],\n                \"hosts\": report.get(\"network\", {}).get(\"hosts\", [])\n            },\n            \"dropped_files\": [\n                {\"name\": f[\"name\"], \"sha256\": f[\"sha256\"], \"size\": f[\"size\"]}\n                for f in report.get(\"dropped\", [])\n            ],\n            \"processes\": [\n                {\"name\": p[\"process_name\"], \"pid\": p[\"pid\"], \"command_line\": p.get(\"command_line\", \"\")}\n                for p in report.get(\"behavior\", {}).get(\"processes\", [])\n            ],\n            \"registry_keys\": [\n                k for k in report.get(\"behavior\", {}).get(\"summary\", {}).get(\"regkey_written\", [])\n            ]\n        }\n\n    def submit_to_joesandbox(self, filepath, joe_api_key, joe_url=\"https:\u002F\u002Fjbxcloud.joesecurity.org\u002Fapi\"):\n        \"\"\"Submit to Joe Sandbox Cloud\"\"\"\n        with open(filepath, \"rb\") as f:\n            response = requests.post(\n                f\"{joe_url}\u002Fv2\u002Fsubmission\u002Fnew\",\n                headers={\"Authorization\": f\"Bearer {joe_api_key}\"},\n                files={\"sample\": f},\n                data={\n                    \"systems\": \"w10_64\",\n                    \"internet-access\": False,\n                    \"report-cache\": True\n                }\n            )\n        return response.json()[\"data\"][\"webid\"]\n```\n\n### Step 4: Extract IOCs and Generate Verdict\n\n```python\nclass VerdictGenerator:\n    def __init__(self):\n        self.malicious_threshold = 7  # Cuckoo score threshold\n\n    def generate_verdict(self, pre_screen, sandbox_report):\n        \"\"\"Combine pre-screening and sandbox results for final verdict\"\"\"\n        iocs = {\n            \"ips\": [],\n            \"domains\": [],\n            \"urls\": [],\n            \"hashes\": [],\n            \"registry_keys\": [],\n            \"files_dropped\": []\n        }\n\n        # Extract IOCs from sandbox report\n        if sandbox_report:\n            iocs[\"domains\"] = sandbox_report.get(\"network\", {}).get(\"dns\", [])\n            iocs[\"ips\"] = sandbox_report.get(\"network\", {}).get(\"hosts\", [])\n            iocs[\"urls\"] = [\n                h[\"url\"] for h in sandbox_report.get(\"network\", {}).get(\"http\", [])\n            ]\n            iocs[\"hashes\"] = [\n                f[\"sha256\"] for f in sandbox_report.get(\"dropped_files\", [])\n            ]\n            iocs[\"registry_keys\"] = sandbox_report.get(\"registry_keys\", [])[:10]\n            iocs[\"files_dropped\"] = sandbox_report.get(\"dropped_files\", [])\n\n        # Determine verdict\n        vt_malicious = pre_screen.get(\"virustotal\", {}).get(\"malicious\", 0)\n        sandbox_score = sandbox_report.get(\"score\", 0) if sandbox_report else 0\n        sig_count = len(sandbox_report.get(\"signatures\", [])) if sandbox_report else 0\n\n        combined_score = (vt_malicious * 2) + (sandbox_score * 10) + (sig_count * 5)\n\n        if combined_score >= 100:\n            verdict = \"MALICIOUS\"\n            confidence = \"HIGH\"\n        elif combined_score >= 50:\n            verdict = \"SUSPICIOUS\"\n            confidence = \"MEDIUM\"\n        elif combined_score >= 20:\n            verdict = \"POTENTIALLY_UNWANTED\"\n            confidence = \"LOW\"\n        else:\n            verdict = \"CLEAN\"\n            confidence = \"HIGH\"\n\n        return {\n            \"verdict\": verdict,\n            \"confidence\": confidence,\n            \"combined_score\": combined_score,\n            \"iocs\": iocs,\n            \"vt_detections\": vt_malicious,\n            \"sandbox_score\": sandbox_score,\n            \"signatures\": sandbox_report.get(\"signatures\", []) if sandbox_report else []\n        }\n```\n\n### Step 5: Push Results to SIEM\n\n```python\ndef push_to_splunk(verdict_result, splunk_url, splunk_token):\n    \"\"\"Send malware analysis verdict to Splunk HEC\"\"\"\n    import json\n\n    event = {\n        \"sourcetype\": \"malware_analysis\",\n        \"source\": \"malware_pipeline\",\n        \"event\": {\n            \"sha256\": verdict_result[\"sha256\"],\n            \"verdict\": verdict_result[\"verdict\"],\n            \"confidence\": verdict_result[\"confidence\"],\n            \"score\": verdict_result[\"combined_score\"],\n            \"vt_detections\": verdict_result[\"vt_detections\"],\n            \"sandbox_score\": verdict_result[\"sandbox_score\"],\n            \"malware_family\": verdict_result.get(\"threat_label\", \"Unknown\"),\n            \"iocs\": verdict_result[\"iocs\"],\n            \"signatures\": [s[\"name\"] for s in verdict_result[\"signatures\"]]\n        }\n    }\n\n    response = requests.post(\n        f\"{splunk_url}\u002Fservices\u002Fcollector\u002Fevent\",\n        headers={\n            \"Authorization\": f\"Splunk {splunk_token}\",\n            \"Content-Type\": \"application\u002Fjson\"\n        },\n        json=event,\n        verify=not os.environ.get(\"SKIP_TLS_VERIFY\", \"\").lower() == \"true\",  # Set SKIP_TLS_VERIFY=true for self-signed certs in lab environments\n    )\n    return response.status_code == 200\n\ndef push_iocs_to_blocklist(iocs, firewall_api):\n    \"\"\"Push extracted IOCs to blocking infrastructure\"\"\"\n    for ip in iocs.get(\"ips\", []):\n        requests.post(\n            f\"{firewall_api}\u002Fblock\",\n            json={\"type\": \"ip\", \"value\": ip, \"action\": \"block\", \"source\": \"malware_pipeline\"}\n        )\n    for domain in iocs.get(\"domains\", []):\n        requests.post(\n            f\"{firewall_api}\u002Fblock\",\n            json={\"type\": \"domain\", \"value\": domain, \"action\": \"sinkhole\", \"source\": \"malware_pipeline\"}\n        )\n```\n\n### Step 6: Orchestrate the Full Pipeline\n\n```python\ndef run_malware_pipeline(sample_path, config):\n    \"\"\"Execute full malware analysis pipeline\"\"\"\n    collector = MalwareCollector()\n    screener = MalwarePreScreener(config[\"vt_key\"])\n    submitter = SandboxSubmitter(config[\"cuckoo_url\"])\n    generator = VerdictGenerator()\n\n    # Step 1: Hash and pre-screen\n    hashes = collector.compute_hashes(sample_path)\n    pre_screen = screener.pre_screen(hashes[\"sha256\"])\n\n    # Step 2: Submit to sandbox if unknown\n    sandbox_report = None\n    if pre_screen[\"needs_sandbox\"]:\n        task_id = submitter.submit_to_cuckoo(sample_path)\n        sandbox_report = submitter.wait_for_analysis(task_id)\n\n    # Step 3: Generate verdict\n    verdict = generator.generate_verdict(pre_screen, sandbox_report)\n    verdict[\"sha256\"] = hashes[\"sha256\"]\n    verdict[\"threat_label\"] = pre_screen.get(\"virustotal\", {}).get(\"threat_label\", \"Unknown\")\n\n    # Step 4: Push to SIEM\n    push_to_splunk(verdict, config[\"splunk_url\"], config[\"splunk_token\"])\n\n    # Step 5: Block if malicious\n    if verdict[\"verdict\"] == \"MALICIOUS\":\n        push_iocs_to_blocklist(verdict[\"iocs\"], config[\"firewall_api\"])\n\n    screener.close()\n    return verdict\n```\n\n## Key Concepts\n\n| Term | Definition |\n|------|-----------|\n| **Dynamic Analysis** | Executing malware in a sandbox to observe runtime behavior (process creation, network, file system changes) |\n| **Static Analysis** | Examining malware without execution (hash lookup, string analysis, PE header inspection) |\n| **Sandbox Evasion** | Techniques malware uses to detect sandbox environments and alter behavior to avoid analysis |\n| **IOC Extraction** | Automated process of identifying network indicators, file artifacts, and registry changes from sandbox reports |\n| **Multi-AV Scanning** | Submitting samples to multiple antivirus engines (VirusTotal) for consensus-based detection |\n| **Verdict** | Final classification of a sample: Malicious, Suspicious, Potentially Unwanted, or Clean |\n\n## Tools & Systems\n\n- **Cuckoo Sandbox**: Open-source automated malware analysis platform with behavioral analysis and network capture\n- **Joe Sandbox**: Commercial sandbox with deep behavioral analysis, YARA matching, and MITRE ATT&CK mapping\n- **Any.Run**: Interactive sandbox service allowing real-time manipulation during analysis for debugging evasive malware\n- **VirusTotal**: Multi-engine scanning service providing 70+ AV results and behavioral analysis reports\n- **CAPE Sandbox**: Community-maintained Cuckoo fork with enhanced payload extraction and configuration dumping\n\n## Common Scenarios\n\n- **Email Attachment Triage**: Auto-submit quarantined email attachments, generate verdict in \u003C5 minutes\n- **EDR Quarantine Processing**: Batch-process files quarantined by endpoint security for detailed analysis\n- **Incident Investigation**: Submit suspicious binaries found during IR for malware family identification and IOC extraction\n- **Threat Intel Enrichment**: Analyze samples from threat feeds to extract C2 infrastructure and update blocking\n- **Zero-Day Detection**: Sandbox catches novel malware missed by signature-based AV through behavioral analysis\n\n## Output Format\n\n```\nMALWARE ANALYSIS REPORT — Pipeline Submission\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\nSample:       invoice_march.docx\nSHA256:       a1b2c3d4e5f6a7b8...\nFile Type:    Microsoft Word Document (macro-enabled)\n\nPre-Screening:\n  VirusTotal:    34\u002F72 malicious (Emotet.Downloader)\n  MalwareBazaar: Tags: emotet, macro, downloader\n\nSandbox Analysis (Cuckoo):\n  Score:         9.2\u002F10 (MALICIOUS)\n  Signatures:\n    - Macro executes PowerShell download cradle (severity: 8)\n    - Process injection into explorer.exe (severity: 9)\n    - Connects to known Emotet C2 server (severity: 9)\n\nExtracted IOCs:\n  C2 IPs:       185.234.218[.]50:8080, 45.77.123[.]45:443\n  Domains:       update-service[.]evil[.]com\n  Dropped Files: payload.dll (SHA256: b2c3d4e5...)\n  Registry:      HKCU\\Software\\Microsoft\\Windows\\CurrentVersion\\Run\\Update\n\nVERDICT: MALICIOUS (Emotet Downloader) — Confidence: HIGH\nACTIONS:\n  [DONE] IOCs pushed to Splunk threat intel\n  [DONE] C2 IPs blocked on firewall\n  [DONE] Domain sinkholed on DNS\n  [DONE] Hash blocked on endpoint\n```\n",{"hide":49,"name":5,"source":50,"license":15,"description":7,"authorized_lab":45,"origin_frontmatter":51},true,"mukul975\u002FAnthropic-Cybersecurity-Skills","name: building-automated-malware-submission-pipeline | description: 'Builds an automated malware submission and analysis pipeline that collects |   suspicious files from endpoints and email gateways, submits them to sandbox environments |   and multi-engine scanners, and generates verdicts with IOCs for SIEM integration. |   Use when SOC teams need to scale malware analysis beyond manual sandbox submissions |   for high-volume alert triage. |  |   ' | domain: cybersecurity | subdomain: soc-opera","main","4c6d8d65f3d6096e2fc25b0845e481dda73c2794",".claude\u002Fskills\u002Fcyber-building-automated-malware-submission-pipeline",0,"https:\u002F\u002Fgithub.com\u002Fnexuslinkproductions\u002Fyuri-os","https:\u002F\u002Fgithub.com\u002Fnexuslinkproductions","Building deterministic AI governance and continuity systems. Workflow architect + visual storyteller","2026-11-11 16:42:59",{"source":8,"skillName":5,"commands":61,"prompt":71,"zipAvailable":49},[62,65,68],{"tool":63,"command":64},"npx","npx skills add nexuslinkproductions\u002Fyuri-os --skill cyber-building-automated-malware-submission-pipeline",{"tool":66,"command":67},"bunx","bunx skills add nexuslinkproductions\u002Fyuri-os --skill cyber-building-automated-malware-submission-pipeline",{"tool":69,"command":70},"pnpm","pnpm dlx skills add nexuslinkproductions\u002Fyuri-os --skill cyber-building-automated-malware-submission-pipeline","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fnexuslinkproductions\u002Fyuri-os\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fcyber-building-automated-malware-submission-pipeline\u002FSKILL.md",[],[74,97,120,145,174,193],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":78,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":44},"01M71CG1AME5WC0A79AE65WT0X","zoom-out","Tell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a section of code or need to understand how it fits into the bigger picture.","MIT","https:\u002F\u002Fgithub.com\u002Fnexuslinkproductions\u002Fyuri-os\u002Fblob\u002Fmain\u002Fskills\u002Fzoom-out\u002FSKILL.md",[],[82,83,84,85,86,87,88,89,90,91,92,39,93,94,95,96],"zoom out","zoom","with","harness","how","section","re","true","understand","use","perspective","you","code","it","context",{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":78,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"publishedAt":44},"01M71CFY9ATD0BAXV6B14HFG7C","yuri-shura","6-perspective adversarial review for high-stakes turns (architecture decisions, refactor planning, deployment review) — fans out architect, adversary (7-vector attack), maintainer, ops, product, and security perspectives in parallel, then consolidates. Use when user says 'review this decision', '\u002Fshura', 'adversarial review', 'what could go wrong', 'architecture review', or 'deployment review'.","https:\u002F\u002Fgithub.com\u002Fnexuslinkproductions\u002Fyuri-os\u002Fblob\u002Fmain\u002Fskills\u002Fyuri-shura\u002FSKILL.md",[],[104,105,85,106,107,29,108,109,110,111,112,91,113,39,114,115,116,117,118,119],"yuri shura","parallel","architecture review","planning","deployment","vector","strategic review","decision","strategic","ops","workflow","decisions","architecture","review","perspectives","adversarial",{"skillNo":121,"name":122,"nameZh":6,"description":123,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":78,"licenseFileUrl":6,"sourceHtmlUrl":124,"categories":125,"keywords":127,"publishedAt":44},"01M71CFTTYW1HA2MNX38EV1GJ5","yuri-sales-intelligence","Unified sales and outreach skill generating cold outreach openers, social selling sequences, objection rebuttals, and ad creative for any paid platform — multi-persona aware, adapting tone and offer frame to buyer type. Use when user says 'write a cold email', 'outreach sequence', 'objection handling', 'ad copy', or 'sales pitch'.","https:\u002F\u002Fgithub.com\u002Fnexuslinkproductions\u002Fyuri-os\u002Fblob\u002Fmain\u002Fskills\u002Fyuri-sales-intelligence\u002FSKILL.md",[126],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[128,129,130,131,132,133,134,135,136,39,137,138,139,140,141,142,30,29,143,144],"intelligence","sales intelligence","yuri sales intelligence","sales","cold","paid","social","persona","pitch","cold email","ad creative","write","sequences","sequence","platform","cold outreach","frame",{"skillNo":146,"name":147,"nameZh":6,"description":148,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":78,"licenseFileUrl":6,"sourceHtmlUrl":149,"categories":150,"keywords":159,"publishedAt":44},"01M71CFQMBFTFADJNGP0Z2WCYK","yuri-code-intelligence","Unified code quality intelligence layer that diagnoses code smells (Long Method, Feature Envy, design pattern issues), prescribes targeted Fowler refactoring techniques, and reviews code for security, performance, and clarity. Use when user says 'review this code', 'refactor this', 'what's wrong with this method', 'code smells', or 'clean this up'.","https:\u002F\u002Fgithub.com\u002Fnexuslinkproductions\u002Fyuri-os\u002Fblob\u002Fmain\u002Fskills\u002Fyuri-code-intelligence\u002FSKILL.md",[151,154],{"categoryNo":152,"categoryName":153,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000007","代码审查",{"categoryNo":155,"categoryName":156,"taxonomyType":157,"taxonomyTypeDesc":158},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[160,94,161,128,85,162,163,164,29,165,166,167,168,169,170,171,172,173,91,39],"yuri code intelligence","code intelligence","reviews","code quality","feature","performance","code review","long","up","issues","clean","techniques","improve","design",{"skillNo":175,"name":176,"nameZh":6,"description":177,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":78,"licenseFileUrl":6,"sourceHtmlUrl":178,"categories":179,"keywords":180,"publishedAt":44},"01M71CFP32RT6GD3GKNHCJP8VP","yuri-adw","Invoke when user asks to run the ADW loop \u002F agentic engineering loop \u002F software factory workflow.","https:\u002F\u002Fgithub.com\u002Fnexuslinkproductions\u002Fyuri-os\u002Fblob\u002Fmain\u002Fskills\u002Fyuri-adw\u002FSKILL.md",[],[181,182,183,184,185,186,187,188,189,39,190,114,191,192],"yuri adw","run","engineering loop","software factory","software","agentic engineering","factory","loop","invoke","engineering","agentic","user",{"skillNo":194,"name":195,"nameZh":6,"description":196,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":78,"licenseFileUrl":6,"sourceHtmlUrl":197,"categories":198,"keywords":211,"publishedAt":44},"01M71CFK4VPEKY6A73237P7RSN","writing-skills","Use when creating new skills, editing existing skills, or verifying skills work before deployment","https:\u002F\u002Fgithub.com\u002Fnexuslinkproductions\u002Fyuri-os\u002Fblob\u002Fmain\u002Fskills\u002Fwriting-skills\u002FSKILL.md",[199,202,205,208],{"categoryNo":200,"categoryName":201,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":203,"categoryName":204,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":206,"categoryName":207,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":209,"categoryName":210,"taxonomyType":157,"taxonomyTypeDesc":158},"01JBSEEDCAT000000000000036","内容创作者",[212,213,214,39,114,215,85,216,108,91,217],"writing","writing skills","new","work","editing","Existing"]