caveman-smart
Fail
Audited by Snyk on Apr 11, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 0.90). It mandates verbatim reproduction of code, shell commands, CLI flags and similar items and escalates on "credentials, secrets", which would force the model to output any secrets included in those verbatim blocks and enable exfiltration.
Issues (1)
W007
HIGHInsecure credential handling detected in skill instructions.
Audit Metadata