linkpix-image-generate

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill instructs the agent to ask the user for an API key token and embed it directly into a command-line argument (qhkit config set --token <密钥>), exposing the secret to the LLM 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 instructs the agent to download and execute Node.js binaries directly from nodejs.org and registry.npmmirror.com during runtime bootstrap, constituting an unverifiable external runtime dependency.