review-security
Fail
Audited by Snyk on Feb 28, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 0.80). The prompt instructs the agent to scan for and report hardcoded secrets using regexes and example matches but does not require redaction or prohibit including matched secret values verbatim in reports, so the LLM may need to output secrets as evidence.
Audit Metadata