linkpix-video-translate

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 and pass it directly to the CLI command via qhkit config set --token <密钥>, which handles a secret value verbatim in the output/command.

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 Node.js package (@iqinghu/qhkit) and Node.js binaries from npmmirror/nodejs.org during runtime setup, constituting an operational dependency from an unofficial/third-party registry source (iqinghu.com).