hardcoded-secrets-anti-pattern
Fail
Audited by Snyk on Feb 16, 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 both includes literal example secrets (e.g., sk-live..., SG..., hardcoded passwords) and instructs the agent to detect and report embedded secrets in code, which encourages the LLM to identify and potentially output secret values verbatim.
Audit Metadata