x-twitter

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow calls UnifAPI operations that fetch public X data (e.g., x/users/by/username/{username}, x/users/{id}/tweets, x/tweets/search/recent, x/users/{id}/followers), and those responses include outsider-authored free text like tweet/post content and profile bios that the agent ingests into LLM context.