facebook-page-profile-posts

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

• Third-party content exposure detected (high risk: 0.95). The skill fetches and parses Facebook GraphQL response data at runtime (e.g., text, textReferences, media.ocrText) from the target page/profile timeline, which is outsider-authored free text from non-operating-user accounts and is inserted into the agent’s LLM context via the returned JSON fields.