git-workflow

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 parses PR threads and issue comments from pull requests (e.g., via "agent-tools-gh pr threads --pr <pr_number>" and "agent-tools-gh pr issue-comments-latest ...") and then interprets those comment bodies to decide fixes and push code, so untrusted, user-generated PR/comment content can directly influence the agent's actions.