qinghu-door-outfit-change

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill instructs the agent to obtain a token from the user and pass it via command-line argument (qhkit config set --token <密钥>), which exposes the secret value directly through the agent's execution context and output.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill contains setup and runtime instructions to download and execute Node.js from nodejs.org and npmmirror.com, and to install and execute a third-party npm package (@iqinghu/qhkit), constituting a weak/unknown/suspicious external operational dependency.