linkpix-image-variations

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/key and pass it directly as a command-line argument (qhkit config set --token <密钥>), which causes the secret to pass through the LLM context and command execution output insecurely.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs runtime installation of Node.js binaries and packages from nodejs.org and npmmirror.com which constitutes an operational runtime external dependency.