explain-this-pr

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and reads untrusted, user-generated GitHub PR data (PR body, diff, commits, and comments) via gh pr view / gh pr diff as described in SKILL.md Step 2, and uses that content to generate and post comments, so external PR content can directly influence the agent's outputs and actions.