gcp-secret-manager

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt includes literal secret values and commands that echo or embed those secrets verbatim (e.g., echoing "S3cur3P@ssw0rd!" and a JSON with a password into gcloud, and examples that print secret contents), which requires the LLM to handle and could cause it to output secrets exactly as given.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.80). I flagged the container image URL gcr.io/my-project/myapp:v1.0.0 because the provided Kubernetes manifest pulls and runs that remote image at runtime, which means external code is fetched and executed as a required dependency.