qinghu-viral-video-toolkit

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

• Third-party content exposure detected (medium risk: 0.30). The workflow takes a user-supplied video link (resourceUrl), fetches it via backend tools (qhkit video-inspire), and processes the resulting script/transcription, allowing outsider-authored video content and transcripts to enter the agent's context.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs downloading and installing Node.js binaries and packages from nodejs.org and npmmirror.com during setup/runtime, which constitutes an operational dependency.