x-twitter-scraper

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly instructs the agent to fetch and read user-generated X/Twitter content via the Xquik API (e.g., "Search X for tweets", "read the tweet replies", endpoints like /x/tweets/search and /x/users/{username}), so untrusted third-party tweets/replies/profiles can directly influence actions such as drafting replies, selecting giveaway winners, monitoring, and posting.