pr-fix-loop

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

• Third-party content exposure detected (high risk: 0.90). The skill's scripts (e.g., scripts/check-pr-feedback.sh, scripts/check-new-feedback.sh, and wait-for-reviews.sh) use the GitHub CLI and gh api to fetch PR conversation comments, inline comments, and review bodies (user-generated, public content) and the SKILL.md explicitly instructs the agent to read and act on that feedback to make commits/invoke agents, so untrusted third‑party content can materially influence the agent's actions.