pr-reviewer

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 comments and review threads from GitHub (e.g., via gh api repos/{owner}/{repo}/pulls/{pr}/comments and the reviewThreads GraphQL query), which are untrusted third-party content that the agent ingests and acts on.