audience-fit-check

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

• Third-party content exposure detected (high risk: 0.95). The skill’s required runtime workflow uses UnifAPI to fetch and ingest outsider-authored public content (e.g., creator posts/tweets/videos and engagement samples like x/tweets/{id}/liking_users and x/users/{id}/followers, plus TikTok/IG comment threads), which are readable text authored by non-operator parties and then placed into the agent’s LLM context for analysis.