caveman
Fail
Audited by Snyk on Jul 24, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 1.00). Skill mandates preserving code blocks and "exact error strings verbatim" and keeping API/CLI names and code unchanged, which will force the model to echo any secrets or keys users include verbatim (high exfiltration risk).
Issues (1)
W007
HIGHInsecure credential handling detected in skill instructions.
Audit Metadata