compound-docs
Fail
Audited by Snyk on Mar 5, 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 mandates copying exact error messages and code/config changes verbatim and asks users for detailed inputs, which can force the model to include API keys, tokens, or passwords present in conversation or configs (exfiltration risk).
Audit Metadata