cook-auto
Fail
Audited by Snyk on Apr 29, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 1.00). The prompt mandates showing grep/file:line evidence and writing analysis files (citing file contents) for every claim, which forces the LLM to reproduce repository file lines verbatim and could exfiltrate any embedded API keys, tokens, or passwords found there.
Issues (1)
W007
HIGHInsecure credential handling detected in skill instructions.
Audit Metadata