creator-analytics

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

• Third-party content exposure detected (high risk: 0.85). The required workflow fetches recent posts and profile data from external platform APIs based on a user-supplied URL/@handle, and those fetched post texts/bios are then used to compute and summarize content—this is outsider-authored free text entering the LLM context via the “Fetch the profile” / “Fetch recent posts” runtime path.