code-review
Warn
Audited by Snyk on Mar 10, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill's workflow explicitly runs "gh pr diff" for PR numbers (see "PR 번호가 주어진 경우: gh pr diff 실행" and the "PR #123" example in SKILL.md), meaning the agent fetches and interprets public GitHub PR diffs—untrusted, user-generated third-party content that can materially influence follow-up review actions.
Audit Metadata