follow-up-on-pr

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to fetch a GitHub PR via "FetchUrl (or gh pr view)" and to read reviewer comments, PR description, and CI logs (user-generated content on a public repo), which the agent must interpret and act on to change code and push updates, so untrusted third-party content can influence behavior.