[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77TYM8HMZ9BGSZ8KH34W548":3,"skill-same:01M77TYM8HMZ9BGSZ8KH34W548":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":36,"commitSha":37,"skillDirectory":38,"forksCount":39,"repositoryHtmlUrl":40,"repositoryHomepageUrl":41,"ownerHtmlUrl":42,"ownerBlogUrl":6,"ownerDescription":43,"updatedAt":44,"install":45,"resources":57},"01M77TYM8HMZ9BGSZ8KH34W548","skill-install-guardian",null,"Security and due diligence layer for installing external skills from ClawHub. Performs DEEP content scanning for malicious patterns, security checks, integration analysis, and requires owner confirmation before installation.","Lord1Egypt\u002Fawesome-skill-forge","Lord1Egypt","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F99746359?v=4","01M7592YDNT0XK9WJ0T2MQVPDN","Mohamed Mounir Ali AL Keshita","01M75GRFNHC8VZNWEB8DKDE433",3,"MIT","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fclawhub\u002Fs\u002Fskill-install-guardian\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: skill-install-guardian\ndescription: \"Security and due diligence layer for installing external skills from ClawHub. Performs DEEP content scanning for malicious patterns, security checks, integration analysis, and requires owner confirmation before installation.\"\nversion: \"1.3.0\"\nmetadata:\n  {\"openclaw\":{\"emoji\":\"🛡️\",\"requires\":{\"bins\":[\"npx\"]}, \"tags\":[\"security\", \"installation\", \"due-diligence\", \"skill\"]}}\n---\n\n# Skill Install Guardian\n\n> \"Trust but verify. Always.\"\n\nThis skill protects your workspace by performing security and due diligence checks before installing any external skill.\n\n---\n\n## Purpose\n\nBefore installing any external skill from ClawHub, this skill:\n1. **Deep Content Scan** - Fetches and analyzes actual file contents for malicious patterns\n2. **Verifies** the skill is safe (security checks via ClawHub API)\n3. **Analyzes** file metadata from ClawHub (filenames, structure)\n4. **Checks** if it fits your architecture (integration check)\n5. **Reports** findings to owner\n6. **Requires** confirmation before install\n\n---\n\n## Deep Content Scanning\n\n### What It Does\n\nThis skill performs **actual content analysis** on skill files:\n- Fetches SKILL.md and script files (.py, .js, .sh)\n- Scans for dangerous patterns in file contents\n- Detects: command injection, API keys, hardcoded secrets, obfuscated code\n\n### Security Patterns Detected\n\n| Pattern | Severity | Example |\n|---------|----------|---------|\n| `eval()` | CRITICAL | Code execution |\n| `exec()` | CRITICAL | Code execution |\n| `subprocess` | HIGH | Shell commands |\n| API keys\u002Ftokens | CRITICAL | `sk-xxx`, `ghp_xxx` |\n| `base64` decode | MEDIUM | Obfuscation |\n| `__import__` | MEDIUM | Dynamic imports |\n\n### ⚠️ Security Notes\n\n- **Does NOT execute** any fetched code - only analyzes text\n- **Can produce false positives** - always review findings\n- **Owner must confirm** - automated check, not definitive\n- **Read-only** - only fetches and scans, never executes\n\n---\n\n## Workflow\n\n### Phase 1: Security Check v1 - ClawHub Report\n\n```bash\n# Get skill security report\nnpx clawhub inspect \u003Cskill-slug> --security\n```\n\n**What to check:**\n- Known vulnerabilities\n- Malicious code patterns\n- Suspicious API calls\n- Data exfiltration risks\n\n**Action if flagged:** → ABORT immediately\n\n---\n\n### Phase 2: Security Check v2 - Code Analysis\n\n```bash\n# Fetch skill files\nnpx clawhub inspect \u003Cskill-slug> --files\n\n# Analyze each file for:\n# - Prompt injection patterns\n# - Suspicious API calls (curl, fetch to unknown domains)\n# - Hardcoded secrets\u002Fkeys\n# - Eval() or code execution\n# - Base64 encoded strings (potential obfuscation)\n# - External network calls without justification\n```\n\n**Analysis criteria:**\n| Pattern | Risk Level | Action |\n|---------|------------|--------|\n| `eval(` | CRITICAL | ABORT |\n| `subprocess` without params | HIGH | Flag for review |\n| `curl` to unknown domain | HIGH | Flag for review |\n| Hardcoded API key | CRITICAL | ABORT |\n| Base64 encoded blob | MEDIUM | Flag for review |\n| External URL fetch | MEDIUM | Flag for review |\n| Clean code | LOW | Pass |\n\n**Assumption:** All external skills are potentially malicious until proven otherwise.\n\n---\n\n### Phase 3: Integration Check - Architecture Fit\n\n**Questions to answer:**\n1. **Purpose:** Does this skill solve a real need?\n2. **Conflict:** Does a similar skill already exist?\n3. **Value:** Will this be used, or just clutter?\n4. **Architecture:** Does it fit the workspace structure?\n\n**Check existing skills:**\n```bash\nnpx clawhub search \u003Crelated-topic>\nls skills\u002F*\u002FSKILL.md | xargs grep -l \"\u003Ctopic>\"\n```\n\n**Conflict detection:**\n- Similar functionality → Flag as potential duplicate\n- No clear use case → Flag as low value\n\n---\n\n### Phase 4: Report to Owner\n\nGenerate a report with:\n\n```markdown\n## Skill Install Report: \u003Cskill-name>\n\n### Security Status\n- [ ] PASSED \u002F [ ] FAILED\n\n### Security Details\n- ClawHub report: \u003Cstatus>\n- Code analysis: \u003Cfindings>\n\n### Integration Status\n- Purpose: \u003Cuseful\u002Fuseless>\n- Conflicts: \u003Clist>\n- Value: \u003Chigh\u002Fmedium\u002Flow>\n\n### Recommendation\n[PROCEED] \u002F [ABORT] \u002F [REVIEW]\n\n### Owner Decision Required\nPlease confirm before I proceed with installation.\n```\n\n---\n\n## Usage\n\n### Run Full Security Check\n\n```bash\npython3 skills\u002Fskill-install-guardian\u002Fscripts\u002Fcheck.py \u003Cskill-slug>\n```\n\n### Quick Check (skip analysis)\n\n```bash\npython3 skills\u002Fskill-install-guardian\u002Fscripts\u002Fcheck.py \u003Cskill-slug> --quick\n```\n\n### Install After Approval\n\n```bash\nnpx clawhub install \u003Cskill-slug>\n```\n\n---\n\n## Integration with Workflow\n\n### Before Any Install\n\n```\n1. Owner: \"Install skill X\"\n2. Me: Run skill-install-guardian\n3. Guardian: Security Check v1\n4. Guardian: Security Check v2 (if v1 passes)\n5. Guardian: Integration Check\n6. Guardian: Report to owner\n7. Owner: Confirm or abort\n8. If confirmed: Install\n```\n\n---\n\n## Output Format\n\n```json\n{\n  \"skill\": \"example-skill\",\n  \"version\": \"1.0.0\",\n  \"security\": {\n    \"v1_clawhub\": \"PASS\",\n    \"v2_code_analysis\": {\n      \"status\": \"PASS\",\n      \"issues_found\": []\n    }\n  },\n  \"integration\": {\n    \"purpose\": \"useful\",\n    \"conflicts\": [],\n    \"value\": \"high\"\n  },\n  \"recommendation\": \"PROCEED\",\n  \"owner_decision\": \"PENDING\"\n}\n```\n\n---\n\n## Safety Principles\n\n### Always Assume\n- External skills may contain malicious code\n- Authors may have good intentions but poor security\n- New versions could introduce threats\n- Hidden payloads may exist in encoded strings\n\n### Never\n- Auto-install without owner confirmation\n- Skip security checks for \"trusted\" authors\n- Assume recent updates are safe\n- Ignore warnings from security tools\n\n### Do\n- Verify every skill manually\n- Check recent reviews\u002Fissues\n- Search for known vulnerabilities\n- Analyze code even for popular skills\n\n---\n\n## Related Skills\n\n- [[workspace-analyzer]] - Analyze installed skills\n- [[skill-creator]] - Create skills safely\n\n---\n\n## Changelog\n\n### v1.3.0 (2026-02-21)\n- **DEEP CONTENT SCANNING** - Now actually fetches and scans file contents\n- Scans SKILL.md, .py, .js, .sh files for dangerous patterns\n- Detects: subprocess, API keys, tokens eval(), exec(),, obfuscation\n- Added comprehensive security patterns list\n- Clear security notes about what it does\u002Fdoesn't do\n\n### v1.2.0 (2026-02-21)\n- Fixed documentation to accurately reflect limitations\n- Removed unused curl from required binaries\n- Added limitation notes (no content analysis, reads local skills dir)\n- Clarified this provides warnings, not definitive security\n\n### v1.1.0 (2026-02-21)\n- Fixed command injection vulnerability (slug validation)\n- Changed from shell=True to list-based subprocess calls\n- Fixed typo in SAFE_DOMAINS\n- Added slug validation function\n- Stricter handling of invalid slugs\n\n### v1.0.0 (2026-02-21)\n- Initial release\n- Two-layer security check\n- Integration analysis\n- Owner confirmation workflow\n\n---\n\n*Security first. Always verify.*\n","# Skill Install Guardian\n\n> \"Trust but verify. Always.\"\n\nThis skill protects your workspace by performing security and due diligence checks before installing any external skill.\n\n---\n\n## Purpose\n\nBefore installing any external skill from ClawHub, this skill:\n1. **Deep Content Scan** - Fetches and analyzes actual file contents for malicious patterns\n2. **Verifies** the skill is safe (security checks via ClawHub API)\n3. **Analyzes** file metadata from ClawHub (filenames, structure)\n4. **Checks** if it fits your architecture (integration check)\n5. **Reports** findings to owner\n6. **Requires** confirmation before install\n\n---\n\n## Deep Content Scanning\n\n### What It Does\n\nThis skill performs **actual content analysis** on skill files:\n- Fetches SKILL.md and script files (.py, .js, .sh)\n- Scans for dangerous patterns in file contents\n- Detects: command injection, API keys, hardcoded secrets, obfuscated code\n\n### Security Patterns Detected\n\n| Pattern | Severity | Example |\n|---------|----------|---------|\n| `eval()` | CRITICAL | Code execution |\n| `exec()` | CRITICAL | Code execution |\n| `subprocess` | HIGH | Shell commands |\n| API keys\u002Ftokens | CRITICAL | `sk-xxx`, `ghp_xxx` |\n| `base64` decode | MEDIUM | Obfuscation |\n| `__import__` | MEDIUM | Dynamic imports |\n\n### ⚠️ Security Notes\n\n- **Does NOT execute** any fetched code - only analyzes text\n- **Can produce false positives** - always review findings\n- **Owner must confirm** - automated check, not definitive\n- **Read-only** - only fetches and scans, never executes\n\n---\n\n## Workflow\n\n### Phase 1: Security Check v1 - ClawHub Report\n\n```bash\n# Get skill security report\nnpx clawhub inspect \u003Cskill-slug> --security\n```\n\n**What to check:**\n- Known vulnerabilities\n- Malicious code patterns\n- Suspicious API calls\n- Data exfiltration risks\n\n**Action if flagged:** → ABORT immediately\n\n---\n\n### Phase 2: Security Check v2 - Code Analysis\n\n```bash\n# Fetch skill files\nnpx clawhub inspect \u003Cskill-slug> --files\n\n# Analyze each file for:\n# - Prompt injection patterns\n# - Suspicious API calls (curl, fetch to unknown domains)\n# - Hardcoded secrets\u002Fkeys\n# - Eval() or code execution\n# - Base64 encoded strings (potential obfuscation)\n# - External network calls without justification\n```\n\n**Analysis criteria:**\n| Pattern | Risk Level | Action |\n|---------|------------|--------|\n| `eval(` | CRITICAL | ABORT |\n| `subprocess` without params | HIGH | Flag for review |\n| `curl` to unknown domain | HIGH | Flag for review |\n| Hardcoded API key | CRITICAL | ABORT |\n| Base64 encoded blob | MEDIUM | Flag for review |\n| External URL fetch | MEDIUM | Flag for review |\n| Clean code | LOW | Pass |\n\n**Assumption:** All external skills are potentially malicious until proven otherwise.\n\n---\n\n### Phase 3: Integration Check - Architecture Fit\n\n**Questions to answer:**\n1. **Purpose:** Does this skill solve a real need?\n2. **Conflict:** Does a similar skill already exist?\n3. **Value:** Will this be used, or just clutter?\n4. **Architecture:** Does it fit the workspace structure?\n\n**Check existing skills:**\n```bash\nnpx clawhub search \u003Crelated-topic>\nls skills\u002F*\u002FSKILL.md | xargs grep -l \"\u003Ctopic>\"\n```\n\n**Conflict detection:**\n- Similar functionality → Flag as potential duplicate\n- No clear use case → Flag as low value\n\n---\n\n### Phase 4: Report to Owner\n\nGenerate a report with:\n\n```markdown\n## Skill Install Report: \u003Cskill-name>\n\n### Security Status\n- [ ] PASSED \u002F [ ] FAILED\n\n### Security Details\n- ClawHub report: \u003Cstatus>\n- Code analysis: \u003Cfindings>\n\n### Integration Status\n- Purpose: \u003Cuseful\u002Fuseless>\n- Conflicts: \u003Clist>\n- Value: \u003Chigh\u002Fmedium\u002Flow>\n\n### Recommendation\n[PROCEED] \u002F [ABORT] \u002F [REVIEW]\n\n### Owner Decision Required\nPlease confirm before I proceed with installation.\n```\n\n---\n\n## Usage\n\n### Run Full Security Check\n\n```bash\npython3 skills\u002Fskill-install-guardian\u002Fscripts\u002Fcheck.py \u003Cskill-slug>\n```\n\n### Quick Check (skip analysis)\n\n```bash\npython3 skills\u002Fskill-install-guardian\u002Fscripts\u002Fcheck.py \u003Cskill-slug> --quick\n```\n\n### Install After Approval\n\n```bash\nnpx clawhub install \u003Cskill-slug>\n```\n\n---\n\n## Integration with Workflow\n\n### Before Any Install\n\n```\n1. Owner: \"Install skill X\"\n2. Me: Run skill-install-guardian\n3. Guardian: Security Check v1\n4. Guardian: Security Check v2 (if v1 passes)\n5. Guardian: Integration Check\n6. Guardian: Report to owner\n7. Owner: Confirm or abort\n8. If confirmed: Install\n```\n\n---\n\n## Output Format\n\n```json\n{\n  \"skill\": \"example-skill\",\n  \"version\": \"1.0.0\",\n  \"security\": {\n    \"v1_clawhub\": \"PASS\",\n    \"v2_code_analysis\": {\n      \"status\": \"PASS\",\n      \"issues_found\": []\n    }\n  },\n  \"integration\": {\n    \"purpose\": \"useful\",\n    \"conflicts\": [],\n    \"value\": \"high\"\n  },\n  \"recommendation\": \"PROCEED\",\n  \"owner_decision\": \"PENDING\"\n}\n```\n\n---\n\n## Safety Principles\n\n### Always Assume\n- External skills may contain malicious code\n- Authors may have good intentions but poor security\n- New versions could introduce threats\n- Hidden payloads may exist in encoded strings\n\n### Never\n- Auto-install without owner confirmation\n- Skip security checks for \"trusted\" authors\n- Assume recent updates are safe\n- Ignore warnings from security tools\n\n### Do\n- Verify every skill manually\n- Check recent reviews\u002Fissues\n- Search for known vulnerabilities\n- Analyze code even for popular skills\n\n---\n\n## Related Skills\n\n- [[workspace-analyzer]] - Analyze installed skills\n- [[skill-creator]] - Create skills safely\n\n---\n\n## Changelog\n\n### v1.3.0 (2026-02-21)\n- **DEEP CONTENT SCANNING** - Now actually fetches and scans file contents\n- Scans SKILL.md, .py, .js, .sh files for dangerous patterns\n- Detects: subprocess, API keys, tokens eval(), exec(),, obfuscation\n- Added comprehensive security patterns list\n- Clear security notes about what it does\u002Fdoesn't do\n\n### v1.2.0 (2026-02-21)\n- Fixed documentation to accurately reflect limitations\n- Removed unused curl from required binaries\n- Added limitation notes (no content analysis, reads local skills dir)\n- Clarified this provides warnings, not definitive security\n\n### v1.1.0 (2026-02-21)\n- Fixed command injection vulnerability (slug validation)\n- Changed from shell=True to list-based subprocess calls\n- Fixed typo in SAFE_DOMAINS\n- Added slug validation function\n- Stricter handling of invalid slugs\n\n### v1.0.0 (2026-02-21)\n- Initial release\n- Two-layer security check\n- Integration analysis\n- Owner confirmation workflow\n\n---\n\n*Security first. Always verify.*\n",{"name":5,"version":24,"metadata":25,"description":7},"1.3.0",{"openclaw":26},{"tags":27,"emoji":32,"requires":33},[28,29,30,31],"security","installation","due-diligence","skill","🛡️",{"bins":34},[35],"npx","master","4aa004da461d820f4ea5499e58eb8d196cf99016","community\u002Fclawhub\u002Fs\u002Fskill-install-guardian",0,"https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge","https:\u002F\u002Fskill-explorer-rho.vercel.app","https:\u002F\u002Fgithub.com\u002FLord1Egypt","Unbreakable. Unstoppable. Unmatched⚡.\r\n Speaker of machine tongues 🤖  | World-builder of decentralized dreams 🌐 | Defender of the digital realm🛡️.","2026-06-10 08:21:01",{"source":8,"skillName":5,"commands":46,"prompt":55,"zipAvailable":56},[47,49,52],{"tool":35,"command":48},"npx skills add Lord1Egypt\u002Fawesome-skill-forge --skill skill-install-guardian",{"tool":50,"command":51},"bunx","bunx skills add Lord1Egypt\u002Fawesome-skill-forge --skill skill-install-guardian",{"tool":53,"command":54},"pnpm","pnpm dlx skills add Lord1Egypt\u002Fawesome-skill-forge --skill skill-install-guardian","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fclawhub\u002Fs\u002Fskill-install-guardian\u002FSKILL.md",true,[],[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},"01M785WKJB99G3STR1NF9NRTJW","youtube-content","YouTube transcripts to summaries, threads, blogs.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fyoutube-content\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},"01M785WEFHB0G2S9YA6EPR3H0E","xurl","X\u002FTwitter via xurl CLI: post, search, DM, media, v2 API.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fxurl\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},"01M785W98EDN4EFJXJPMQEHCRC","touchdesigner-mcp","Control a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire connections, execute Python, build real-time visuals. 36 native tools.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Ftouchdesigner-mcp\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},"01M785W5S9FP3QBH2V191E025P","test-driven-development","TDD: enforce RED-GREEN-REFACTOR, tests before code.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Ftest-driven-development\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},"01M785W2AS08NSSH9YATCV6FJB","teams-meeting-pipeline","Operate the Teams meeting summary pipeline via Hermes CLI — summarize meetings, inspect pipeline status, replay jobs, manage Microsoft Graph subscriptions.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fteams-meeting-pipeline\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},"01M785VXKW4T34BTP1SCHW1R7F","systematic-debugging","4-phase root cause debugging: understand bugs before fixing.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fsystematic-debugging\u002FSKILL.md",[],[]]