x-twitter-scraper

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow can ingest outsider-authored free text from Xquik responses—e.g., tweet/user bios, DM text, article body, and event payload data.text—into the agent’s LLM context via the “Read X Data”/“Monitoring And Event Delivery” paths (e.g., GET /x/tweets/search, GET /x/users/{id}, GET /x/dm/{userId}/history, GET /x/articles/{tweetId}, GET /events / webhook deliveries).