youtube-downloader
Download YouTube videos and HLS streams (m3u8) from platforms like Mux, Vimeo, etc. using yt-dlp and ffmpeg. Use this skill when users request downloading videos, extracting audio, handling protected streams with authentication headers, or troubleshooting download issues like nsig extraction failures, 403 errors, or cookie extraction problems.
87
88%
Does it follow best practices?
Impact
78%
1.59xAverage score across 3 eval scenarios
Risky
Do not use without reviewing
Security
3 findings — 1 high severity, 2 medium severity. You should review these findings carefully before considering using this skill.
W007: Insecure credential handling detected in skill instructions
What this means
The skill handles credentials insecurely by requiring the agent to include secret values verbatim in its generated output. This exposes credentials in the agent’s context and conversation history, creating a risk of data exfiltration.
Why it was flagged
Insecure credential handling detected (high risk: 1.00). The skill explicitly instructs copying browser cookies and authentication headers from DevTools into yt-dlp/ffmpeg command lines (e.g., using --cookies-from-browser, --cookies-file, and -headers), which requires embedding session/cookie/token values verbatim in generated commands and thus risks secret exfiltration.
W011: Third-party content exposure detected (indirect prompt injection risk)
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and renders metadata and thumbnails from arbitrary public YouTube URLs (see SKILL.md "Default flow" and scripts/download_video.py: print_video_info and fetch_oembed_info) and uses that untrusted, user-generated third‑party content to choose download behavior (clients, cookies/PO-token flow, retries, and follow-up actions), which could allow indirect prompt injection.
W012: Unverifiable external dependency detected (runtime URL that controls agent)
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
Potentially malicious external URL detected (high risk: 0.90). The skill, at runtime, runs pip installs using the PYPI mirror URL https://pypi.tuna.tsinghua.edu.cn/simple (and pulls/runs the external Docker image brainicism/bgutil-ytdlp-pot-provider), which fetches and executes remote code to provide the PO token provider functionality required for high-quality downloads.
- Repository
- daymade/claude-code-skills
- Commit
392d34c
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.