vp-pr-briefing

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

• Third-party content exposure detected (high risk: 0.85). The skill uses gh pr view to fetch the PR’s body and commits and also fetches linked issues and review thread comment bodies from GitHub at runtime; these are outsider-authored free text (PR/issue/comment authors other than the operating user) that is then ingested into the agent’s LLM context for summarization.