linkpix-white-background

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill instructs the agent to set an API token via command-line argument (--token <密钥>) by asking the user for it, which exposes secrets in the command execution logs.

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 a third-party npm package (@iqinghu/qhkit) and optionally download Node.js binaries from nodejs.org during runtime setup, which constitutes a weak/unknown/suspicious operational dependency because npm packages and node binaries from external registries lack verifiable first-party platform provenance.