triage-issue

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly fetches and processes community GitHub issues and comments (e.g., "gh issue view" in Step 1 and the batch "gh issue list" flow) and feeds reporter diagnostic text into sub-agents and the triage decision/workflow, so untrusted user-generated content can directly influence agent actions.