resolve-pr-comments

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

• Third-party content exposure detected (high risk: 0.90). The skill's Step 1 and the included scripts/fetch-pr-data.sh explicitly fetch GitHub pull request reviewThreads and reviews (user-generated comments) which the agent then interprets in Steps 3–11 to decide fixes, replies, and other actions, so untrusted third-party PR content can influence tool use and behavior.