x

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

• Third-party content exposure detected (high risk: 0.90). SKILL.md includes explicit curl calls to X API endpoints (e.g., "Search Recent Tweets" at https://api.x.com/2/tweets/search/recent and various timeline/user endpoints) that fetch public, user-generated tweets which the agent is expected to read and could contain instructions that influence subsequent actions.