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 workflow calls UnifAPI to fetch and then read outsider-authored public content (e.g., creator posts/videos and engagement data like x/tweets/{id}/liking_users, plus comment threads on TikTok/IG) into the agent’s LLM context as evidence for the fit/safety analysis.