automate-before-manual
Fail
Audited by Snyk on Sep 10, 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 LLM to read raw credential files like PAT tokens and
.envfiles from a local secrets directory, creating a risk that these secrets will pass through the context and be exposed or included verbatim in commands.
Issues (1)
W007
HIGHInsecure credential handling detected in skill instructions.
Audit Metadata