qinghu-viral-video-clone

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 a token/API key and pass it directly on the command line using qhkit config set --token <密钥>, which handles a credential insecurely by exposing it in generated commands.

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

• Third-party content exposure detected (low risk: 0.10). The workflow takes a video URL from the user, generates a script using video-inspire, and then processes content that originates from external video platforms (Douyin/TikTok), representing low risk via user-selected URLs.

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 install npm packages from registry.npmmirror.com during runtime setup, but these external sources are unverified third-party/community or official distribution platforms operating without verifiable cryptographic integrity enforcement for the downloaded binaries, resulting in a high provenance risk.