linkpix-pinduoduo-image

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill instructs the agent to ask the user for an API token and then pass it to the command-line tool via a direct argument (qhkit config set --token <密钥>), which causes the secret to be handled and exposed 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 install and execute @iqinghu/qhkit from npm and download Node.js runtimes from nodejs.org at runtime, which constitute external operational dependencies.