linkpix-happyhorse-sales

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill instructs the agent to ask the user for an API key and pass it via a command-line argument (qhkit config set --token <密钥>), which causes the secret value to be exposed directly in the command output and context.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs the agent to download and install a Node.js runtime and packages from nodejs.org and npmmirror.com during setup, which constitute runtime external dependencies under weak/unknown or third-party unofficial provenance.