code-review
Fail
Audited by Snyk on Feb 26, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 0.80). The skill instructs the agent to read diffs and "tie each finding to concrete code evidence," which would likely require reproducing code snippets (and thus any embedded secrets) verbatim unless explicit redaction is specified, creating an exfiltration risk.
Audit Metadata