clean-followers

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

• Third-party content exposure detected (high risk: 0.90). The skill calls the open xquik API (POST /extractions to https://xquik.com/api/v1) to fetch follower/profile data (untrusted, user-generated content) which the agent is instructed to read and use to flag accounts, so third-party content can materially influence decisions.