gh-daily

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

• Third-party content exposure detected (high risk: 0.90). The skill's Phase 3 "Gather Activity Data" explicitly fetches GitHub issues, PRs, notifications, and comments via gh CLI/gh api (e.g., gh issue list, gh pr list, gh api notifications) and then instructs agents to classify and act on that user-generated GitHub content in Phase 4, so untrusted third-party content is read and used to drive decisions.