pr-review-expert

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md workflow (see "Fetching the Diff" and "Step 1 — Fetch Context") explicitly instructs using gh/glab to fetch PR/MR bodies and diffs from GitHub/GitLab — user-generated, third-party content the agent must read and use to drive its review decisions, so malicious PR text or code could indirectly inject instructions and influence behavior.