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 live public X data (e.g., x/users/by/username/{username}, x/users/{id}/tweets, x/tweets/search/recent), so the agent ingests outsider-authored free text/content from public X responses into the LLM context.