code-review
Warn
Audited by Snyk on Jul 28, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). SKILL “code-review” ingests the user-provided review packet content (e.g., PR/diff text) supplied via the workflow’s runtime prompt/invocation (“Start from the review packet the user already has”), so outsider-authored free text can be included as the diff and evidence packet without selecting a specific item first.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata