clawsec-suite

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

• Third-party content exposure detected (high risk: 0.90). The skill fetches and ingests a community-driven advisory feed (e.g., https://clawsec.prompt.security/advisories/feed.json) and a remote skill catalog (https://clawsec.prompt.security/skills/index.json) at runtime (see SKILL.md, HEARTBEAT.md, hooks/handler.ts and scripts/*), and the agent directly reads and interprets those advisories to block or gate installs and to recommend removals—allowing untrusted, user-generated advisory content to materially influence tool use and next actions.