copilot-review-loop

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly polls and ingests unresolved PR comments from GitHub (via gh api repos/{owner}/{repo}/pulls/{pr}/comments and related gh/gh-copilot-review commands) and then reads and acts on those copilot[bot]/PR comments, which are third-party user/bot-generated content that could carry indirect prompt injections.