douyin-transcribe
Warn
Audited by Snyk on Sep 19, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The skill processes URLs and video files provided by the user, navigates to specific Douyin video pages via browser automation, and transcribes the audio/content, which constitutes fetching user-selected external content.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (medium risk: 0.30). The skill makes API calls to api.groq.com and api.openai.com for speech-to-text and text formatting; Groq is a third-party service with common/reputable unofficial provenance, and OpenAI is an official vendor.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata