triage-meeting-prep

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

• Third-party content exposure detected (high risk: 0.95). Outsider-authored free text from GitHub issues/comments (including other users’ issue bodies and comment bodies) is fetched at runtime via Get-IssueDetails.ps1 using gh issue view and gh api .../timeline, then the agent uses that text for LLM-based area classification and reply drafting.