x-api

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow uses X API calls (e.g., /2/tweets/search/recent, /2/users/.../tweets, /2/users/by/username) that return third-party tweet/user text from X, which the agent would ingest into the LLM context as readable JSON fields like tweet text/description—an outsider-authored free-text source.