moltbook-data-splitting-code

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly fetches and acts on user-generated content from the Moltbook social network (see SKILL.md "Common Operations" — "Browse Hot Posts" and the "API Endpoints" like GET /posts and GET /posts/{id}/comments), so untrusted third-party posts/comments can be read and used to drive replies or other agent actions.