github-pull-request-review-resolve

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and reads user-generated PR review comments and reviewThreads from GitHub (e.g., gh api repos/{owner}/{repo}/pulls/<pr>/comments --paginate and the GraphQL reviewThreads query) and instructs the agent to interpret those comments to decide fixes, resolve threads, and drive actions, exposing it to untrusted third-party content.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill invokes the GitHub API at runtime (e.g., "gh api repos/{owner}/{repo}/pulls//comments" and "gh api graphql ...") to fetch PR review/comment bodies which are injected into the agent's context and can directly influence its instructions and decisions.