cr
Warn
Audited by Snyk on Mar 13, 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 fetches and reads user-generated content from GitHub pull requests (PR_BODY and PR comments) via gh api in references/pr-review.md and teams-review.md when $ARGUMENTS is a PR/URL, so untrusted third-party text is ingested and used to guide review decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata