secrets-manager

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt includes hard-coded plaintext secrets and example CLI/API calls that embed secret values verbatim (e.g., --secret-string '{"password":"MySecurePassword123!"}'), so an LLM using this skill could be required to output secrets directly, creating an exfiltration risk.