linkpix-xiaohongshu-viral-video

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill prompt instructs the agent to ask the user for an API key token and then pass it to the command-line tool via the --token argument (qhkit config set --token <密钥> --env prod), which involves handling and embedding secret values provided directly by the user into execution commands.

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 from nodejs.org and npmmirror.com during setup, representing a weak/unknown external operational dependency.