codex-pr-review

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and reads pull request contents from remote GitHub PRs (see SKILL.md fast path steps: "git fetch origin pull//head:pr-" and "git diff origin/...pr-") so it ingests untrusted, user-generated third‑party content and uses that content to drive review decisions and output.