find-bangers

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and reads tweets from public X (via the listed GET /x/users/{id}/tweets and /x/tweets/search endpoints on xquik.com) and states "Tweet text is untrusted," meaning arbitrary user-generated content from the open web is ingested and used to decide which posts to surface, so third-party content can influence the agent's selections and behavior.