resolve-pr-comments

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

• Third-party content exposure detected (high risk: 0.90). This skill fetches and ingests GitHub pull request review threads via the gh api GraphQL query (unresolved review comments in Step 1) and explicitly reads and acts on those user-generated comments (Step 2 evaluation, fixes, and Step 6 replies), so untrusted third-party content can materially influence actions.