setup-red-skills

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

• Third-party content exposure detected (high risk: 0.90). This skill instructs the agent to read and act on GitHub issues and comments (user-generated content) via the gh CLI (see "Read an issue: gh issue view --comments" and the triage/afk workflows in SKILL.md and issue-tracker-github.md), so untrusted third-party issue/comment content can influence decisions and tool actions.