twitter-intelligence

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

• Third-party content exposure detected (medium risk: 0.30). The skill’s workflow ingests outsider-authored free text at runtime by searching/reading public tweets via SandBase tools like twitter_web_search_timeline and twitter_web_tweet_detail (and related comment/user profile/media tools), where tweet text is authored by external users.