moltbook-patrol

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

• Third-party content exposure detected (high risk: 0.90). The patrol script fetches and processes live, user-generated Moltbook content (e.g., reading https://www.moltbook.com/api/v1/feed, /posts, and /agents/dm/* as well as remote skill.json at https://www.moltbook.com/skill.json), and it explicitly reads/handles feed posts and DMs as part of its workflow, exposing the agent to untrusted third‑party content that could contain indirect prompt injection.