clawsec-clawhub-checker

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

• Third-party content exposure detected (high risk: 0.70). The skill explicitly calls ClawHub inspect/search endpoints and parses their JSON (see scripts/check_clawhub_reputation.mjs and hooks/clawsec-advisory-guardian/lib/reputation.mjs, and SKILL.md/network_egress) to compute reputation scores that gate installation, so untrusted, public ClawHub content directly influences decision-making.