linkpix-vidu-q3-clone

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 and then use it directly in a CLI command (qhkit config set --token <密钥> --env prod), which involves handling and passing user credentials in commands.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). The required workflow uses a video inspiration tool (video-inspire generate) that consumes URLs to videos (such as Douyin or TikTok video links) provided by the user, which can contain outsider-authored free text/scripts.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs the agent to install an npm package from npmjs via @iqinghu/qhkit and node binaries from nodejs.org at runtime, which constitutes an operational dependency.