architecture

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill documents and shows CLI invocations that embed secrets/tokens as literal CLI args (e.g., --clientSecret, --password, Authorization token) and notes that pac args / stdout are logged, so an agent following it could be asked to produce commands containing verbatim secrets, creating an exfiltration risk.