code-review

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

• Third-party content exposure detected (high risk: 0.90). This skill's workflow (SKILL.md) explicitly instructs using gh commands to fetch and read pull request diffs, git blame/history, previous PRs and their comments, and repository CLAUDE.md files from GitHub—all untrusted, user-generated third‑party content that the agent must interpret and that directly drives review decisions and comments.