code-review

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

• Third-party content exposure detected (high risk: 1.00). The skill's workflow (SKILL.md and commands/code-review.md) requires using the GitHub CLI (gh) to fetch and read pull request diffs, git blame/history, and previous PRs/comments from GitHub—user-generated, public content—which agents must read and interpret to decide what issues to flag and what comments to post.