grow-followers

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md typical flow explicitly instructs the agent to GET /x/users/{username} and page GET /x/users/{id}/tweets (and /styles/{username}/performance) to ingest other accounts' user-generated tweets from the open web, and those tweets are analyzed and used to drive recommendations, so untrusted third-party content can influence actions.