timeline

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

• Third-party content exposure detected (high risk: 0.90). This skill directly fetches and returns user-generated content from X (see skill-router.json upstream calls to https://api.x.com for the "home", "user-tweets", and "mentions" actions), so untrusted third-party posts could be read and influence the agent's subsequent behavior.