review-pr

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

• Third-party content exposure detected (high risk: 0.90). The skill's Steps instruct the agent to fetch PR data and unresolved review threads (e.g., "gh pr view --json ..." in Step 1 and "List unresolved review threads" in Step 3), which are user-generated content on GitHub that the agent must read and act on, exposing it to untrusted third-party content that could embed instructions.