huashu-douyin-script
Warn
Audited by Snyk on Nov 16, 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 workflow fetches user-selected Douyin competitor video URLs (yt-dlp download, then Gemini video analysis of the video's on-screen text, narration, and captions), so outsider-authored content is ingested only after the user picks specific items, which makes this low risk.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (medium risk: 0.30). The decisive boundary is setup-time retrieval: install.sh clones installed skill files from the GitHub repository
alchaincyf/Write-Prompt, and its documented invocation fetches and executes install.sh itself from raw.githubusercontent.com. Both are published by an individual (the 花叔 author's personal repository), so provenance is unofficial but not weak, giving a medium tier.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata