linkpix-main-image-optimize

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill prompt instructs the agent to ask the user for an API key token and pass it directly via command line arguments (qhkit config set --token <密钥>), which exposes secret values in plaintext command strings.

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 its mirror during setup, which constitutes an unverifiable runtime external dependency from an unauthenticated domain.