advanced-video-downloader
Fail
Audited by Snyk on Feb 15, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 1.00). The skill instructs embedding API keys and cookies directly into commands and script arguments (e.g.,
--api-key sk-xxx,SILICONFLOW_API_KEY=sk-xxx, passing cookies via cookies.txt and reading cookie values), which would require the agent to request and/or emit secret values verbatim in its output.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and scrapes untrusted, user-generated content—e.g., scripts/twitter_video_downloader.py uses Playwright to search x.com and extract tweet/video URLs and yt-dlp downloads arbitrary public social-media/video URLs which are then transcribed—so the agent ingests and interprets third‑party web/user content.
Audit Metadata