aif-review

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md explicitly instructs fetching and interpreting GitHub PR content via "gh pr view --json" and "gh pr diff " (and can post review comments), which ingests untrusted, user-generated third-party content from public GitHub that can materially influence decisions and tool actions.