{"skill":{"slug":"clawguard1","displayName":"Mithilesh","summary":"ClawGuard governance layer that must run before any SQL, file-system, or API write. Use evaluate_action(action_type, justification, risk_level) to log/author...","tags":{"latest":"1.0.0"},"stats":{"comments":0,"downloads":97,"installsAllTime":0,"installsCurrent":0,"stars":0,"versions":1},"createdAt":1774478230203,"updatedAt":1774478812131},"latestVersion":{"version":"1.0.0","createdAt":1774478230203,"changelog":"ClawGuard Skill v1.0.0\n\n- Introduces a governance layer that logs and authorizes all high-impact or potentially destructive actions before execution.\n- Provides `evaluate_action(action_type, justification, risk_level)` to log actions and automatically block any with risk level 4 or higher.\n- Includes `get_audit_report(limit)` to review recent entries in the persistent SQLite-based audit ledger.\n- Clearly outlines risk levels and mandates justification for each action to ensure a robust audit trail.\n- Designed to be invoked before any SQL, file-system, or API write operation.","license":"MIT-0"},"metadata":null,"owner":{"handle":"mithileshgau","userId":"s177tktwz703s8hreajr6kxhts83j1gb","displayName":"mithileshgau","image":"https://avatars.githubusercontent.com/u/55141824?v=4"},"moderation":{"isSuspicious":true,"isMalwareBlocked":false,"verdict":"suspicious","reasonCodes":["suspicious.llm_suspicious"],"summary":"Detected: suspicious.llm_suspicious","engineVersion":"v2.2.0","updatedAt":1774478812131}}