pr-qa

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill explicitly runs secrets scanning (gitleaks) and shows/returns scan findings (including a sample API key string), which requires the agent to surface matched secret values verbatim in its outputs if found.

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly fetches and processes user-generated GitHub review comments and threads (e.g., gh api repos/{owner}/{repo}/pulls/<PR_NUMBER>/comments and issues/<PR_NUMBER>/comments and GraphQL reviewThreads) and then reads/interprets those comments to determine fixes, replies, and code changes, so untrusted third‑party content can directly influence tool actions.