clawsec-clawhub-checker

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.80). The skill's check_clawhub_reputation.mjs explicitly calls public ClawHub CLI commands (e.g., clawhub inspect --json and clawhub install) and the hooks/clawsec-advisory-guardian/lib/reputation.mjs integrates and parses those outputs (including VirusTotal Code Insight messages) into reputation scores and installation decisions, meaning it consumes untrusted, public third‑party content that can materially change agent behavior.