crane-audit
Warn
Audited by Snyk on Mar 11, 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 required workflow (ALIGHT phase) explicitly fetches PR metadata and the full diff via commands like "gw gh pr view {number}" and "gw gh pr diff {number}", meaning it ingests user-generated GitHub PR content (untrusted third-party text) which the agent reads and uses to drive compliance findings and follow-up actions, creating potential for indirect prompt-injection.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata