explain-pr

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

• Third-party content exposure detected (medium risk: 0.30). The skill ingests outsider-authored PR/MR free text (title/description, commit messages, linked issue text, and diff content) by querying the PR/MR at runtime via gh pr view / glab mr view and git diff/git log, so an outsider can plant prompt-injection-like instructions in those fields that the LLM must read before producing the recap.