code-review
Warn
Audited by Snyk on Apr 21, 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). This skill explicitly runs a final code review "on a pull request" and instructs subagents to "review code" (SKILL.md), which means it ingests user-generated PR code/comments (third-party content) that could contain malicious instructions and influence subagent decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata