{"skill":{"slug":"clawshell-0-1-0","displayName":"Clawshell 0.1.0","summary":"Human-in-the-loop security layer. Intercepts high-risk commands and requires push notification approval.","tags":{"latest":"1.0.0"},"stats":{"comments":0,"downloads":1710,"installsAllTime":2,"installsCurrent":0,"stars":0,"versions":1},"createdAt":1770211907063,"updatedAt":1777524989188},"latestVersion":{"version":"1.0.0","createdAt":1770211907063,"changelog":"Initial release of ClawShell: Human-in-the-loop security layer for shell command execution.\n\n- Intercepts shell commands, analyzes risk, and enforces push notification approval for high-risk operations.\n- Categorizes commands into Critical (blocked), High (approval required), Medium (logged), and Low (allowed).\n- Provides three main tools: `clawshell_bash` (secure command exec), `clawshell_status` (view pending/recent approvals), and `clawshell_logs` (audit logs).\n- Supports push notifications via Pushover or Telegram.\n- Highly configurable through environment variables and `config.yaml`.\n- Enforces all decisions via a persistent JSONL audit log.","license":null},"metadata":{"os":null,"systems":null},"owner":{"handle":"lucky-2968","userId":"publishers:lucky-2968","displayName":"Lucky-2968","image":"https://avatars.githubusercontent.com/u/208146076?v=4"},"moderation":{"isSuspicious":true,"isMalwareBlocked":false,"verdict":"suspicious","reasonCodes":["suspicious.llm_suspicious","suspicious.vt_suspicious"],"summary":"Detected: suspicious.llm_suspicious, suspicious.vt_suspicious","engineVersion":"v2.4.5","updatedAt":1777524989188}}