implement-review-pr

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly directs the agent to fetch and inspect GitHub PR content using gh pr view, gh pr diff, and gh pr checks, which are untrusted, user-generated public inputs that the agent must read and act on to produce reviews and decide follow-up actions, so malicious PR content could influence behavior.