matematic-patron-pr-review-pl

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

• Third-party content exposure detected (medium risk: 0.30). The skill’s required runtime workflow ingests outsider-authored PR diff text from GitHub (e.g., via gh pr diff <N> / gh pr view <N> --json files,additions,deletions in the “Jak prowadzic review” step), so an outsider can submit poison through their PR content for the agent/LLM to read.