vp-pr-briefing

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

• Third-party content exposure detected (high risk: 0.85). This skill fetches and summarizes outsider-authored PR content (PR body, issue bodies, and review thread comment bodies) via the gh pr view and related GitHub API calls, which become readable text in the agent/LLM context at runtime—i.e., indirect prompt injection risk from free-form third-party text.