SKILLEMALL.ai
RU Sign in

CC yt-dlp-downloader

Download videos from YouTube, Bilibili, Twitter, and thousands of other sites using yt-dlp. Use when the user provides a video URL and wants to download it, extract audio (MP3), download subtitles, or select video quality. Triggers on phrases like "下载视频", "download video", "yt-dlp", "YouTube", "B站", "抖音", "提取音频", "extract audio".

Not recommendedcritical or high security findings
modbender/skill-library-mcp Agent Skills author: modbender MIT 1 file body ≈ 1 461 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Download videos from YouTube, Bilibili, Twitter, and thousands of other sites using yt-dlp.

As a process C 62/100 · Has gaps — weak spots: result and completion, consistency

ProcedureYouTubeMedia and videotype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
C
67/100
safety, quality, tests
Safety 60%
53
Quality 40%
89
Run on models
none yet
Process rating
C
62/100
Has gaps
Result and completion w 14
0
Consistency w 8
40
Failures and branches w 10
50
the three weakest of ten parameters · all ten

What is at stake

The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.

Exfiltration
If you install

The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

How to improve

  1. Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 5

  • high Exfiltration intent-browser-credential-store SKILL.md:41
    Accesses a browser credential / cookie store
    yt-dlp -P "~/Downloads/yt-dlp" --cookies-from-browser chrome "YOUTUBE_URL"
  • high Exfiltration intent-browser-credential-store SKILL.md:207
    Accesses a browser credential / cookie store
    yt-dlp -P "~/Downloads/yt-dlp" --cookies-from-browser chrome "YOUTUBE_URL"
Medium and low: 3
  • medium Exfiltration intent-browser-credential-store SKILL.md:121
    Accesses a browser credential / cookie store (quoted — discussed, not commanded)
    - YouTube/YouTube Music → **Always use `--cookies-from-browser chrome`**
    quoted
  • medium Exfiltration intent-browser-credential-store SKILL.md:148
    Accesses a browser credential / cookie store (the skill's own vendor host)
    yt-dlp -P "~/Downloads/yt-dlp" --cookies-from-browser chrome "https://www.youtube.com/watch?v=xxx"
    vendor-host
  • low Exfiltration intent-browser-credential-store SKILL.md:186
    Accesses a browser credential / cookie store (detector / deny-list definition; documentation table row)
    | HTTP 403 Forbidden | YouTube blocks unauthenticated requests | Use `--cookies-from-browser chrome` |
    detectortable

Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

✓ No remarks against the Agent Skills spec

Process rating: all ten parameters 62/100

  • 0Result and completion. Does not say what the result is
  • 40Consistency. Frontmatter name (yt-dlp-downloader) differs from the folder (yt-dlp-downloader-skill)
  • 50Failures and branches. 0 branches, has a failure section
  • 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
  • 70When it triggers. States when to use, but not when not to
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 100Steps. 26 steps
  • 100Execution cost. Instruction body is 1461 tokens
  • 100Running it twice. No mutating operations
  • 100Progress reporting. Reports progress

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +4Description does not say when NOT to use the skill (false activations)
  • +3Output format is not stated: the model decides each time
  • +1No license
  • +2Single-language instructions
  • +5Description quotes 4 example trigger phrases
  • +3Description length 331: enough signal without eating the budget
  • +4Structure: 25 headings
  • +3Step-by-step instructions: 26 items
  • +4Has examples (23 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.