gh-review-requests

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly fetches and reads GitHub notifications and PR data via the gh CLI / gh api (see SKILL.md Step 2 and Fallback), which exposes it to untrusted, user-generated content (PR titles/descriptions, comments, notification payloads) that the agent must interpret to decide which PRs need review and thus could enable indirect prompt injection.