code-review:review-pr

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

• Third-party content exposure detected (high risk: 1.00). SKILL.md explicitly instructs the agent to fetch and analyze pull request and repository files (via git/gh commands such as git diff, and gh api, and by scanning README.md/CLAUDE.md/consitution.md), which are untrusted user-generated third‑party content that the agent must read and use to decide review actions.