pr-review

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

• Third-party content exposure detected (high risk: 0.90). Yes — the skill directly fetches PR metadata, bodies, files and diffs from arbitrary GitHub pull requests using commands like gh pr view <PR> --json ..., gh pr view <PR> --json files, and gh pr diff <PR>, which are user-generated, untrusted third-party content the agent is expected to read and could contain indirect prompt injections.