{"skill":{"slug":"clawshell","displayName":"Clawshell","summary":"Human-in-the-loop security layer. Intercepts high-risk commands and requires push notification approval.","tags":{"latest":"0.1.0"},"stats":{"comments":1,"downloads":2785,"installsAllTime":28,"installsCurrent":26,"stars":7,"versions":1},"createdAt":1770104161958,"updatedAt":1777524972885},"latestVersion":{"version":"0.1.0","createdAt":1770104161958,"changelog":"Initial release of ClawShell: a human-in-the-loop security layer for shell commands.\n\n- Intercepts shell commands, analyzes risk, and requires push notification approval for high-risk actions.\n- Blocks critical commands automatically; allows medium/low-risk commands based on configurable rules.\n- Provides tools for secure shell command execution (`clawshell_bash`), status checks, and log retrieval.\n- Supports Pushover and Telegram for approval notifications.\n- All command decisions and approvals are logged for audit and debugging.\n- Highly configurable via environment variables and `config.yaml`, with support for custom risk rules.","license":null},"metadata":{"os":null,"systems":null},"owner":{"handle":"polucas","userId":"publishers:polucas","displayName":"Jed","image":"https://avatars.githubusercontent.com/u/28898890?v=4"},"moderation":{"isSuspicious":true,"isMalwareBlocked":false,"verdict":"suspicious","reasonCodes":["suspicious.llm_suspicious"],"summary":"Detected: suspicious.llm_suspicious","engineVersion":"v2.4.5","updatedAt":1777524972885}}