facebook

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly reads and acts on untrusted, user-generated Facebook content (e.g., GET /{post-id}/comments in references/comments-moderation.md and GET /{page-id}/posts in references/page-posting.md) and uses that content to drive moderation and posting actions, which could allow indirect prompt injection.