code-review

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to run gh pr view <number> / gh pr diff and "read all new and modified files" from PRs, which means the agent will ingest user-generated GitHub PR content (public third-party material) that could contain instructions influencing its decisions and actions.