sop

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The SOP skill requires filling templates with "real content", asks about "credentials" as required inputs, and mandates AI-agent SOPs include exact commands (without guidance to use environment variables or secret references), which creates a realistic risk the model will be prompted to embed secret values verbatim in commands or code blocks.