SKILLEMALL.ai
GitHub ↗ RU Sign in

DC youtube-downloader

Fetch existing YouTube transcripts/subtitles or archive spoken video content as text, and download YouTube videos/audio or HLS streams (m3u8) with yt-dlp and ffmpeg. Use for transcript/subtitle retrieval, text-first video archiving, video/audio downloads, protected streams with authentication headers, and download failures including nsig, 403 or browser-cookie issues.

Not recommendedcritical or high security findings · low grade D
daymade/claude-code-skills Agent Skills author: daymade MIT 6 files · 2 scripts body ≈ 5 009 tokens Open the sourcegithub.com↗ analyzed 10 d ago

Fetch existing YouTube transcripts/subtitles or archive spoken video content as text, and download YouTube videos/audio or HLS streams (m3u8) with yt-dlp and…

As a process C 57/100 · Has gaps — References files that are not bundled: URL, THUMBNAIL_URL

ProcedureYouTubeGitHubMedia and videotype and topics are labelled automatically from the skill text
Runs in: 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) OpenClaw Goose OpenCode
JSON
Technical rating
D
62/100
safety, quality, tests
Safety 60%
56
Quality 40%
70
Run on models
none yet
Process rating
C
57/100
Has gaps
References files that are not bundled: URL, THUMBNAIL_URL
Tools and files w 18
0
Result and completion w 14
0
When it triggers w 12
70
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.
  2. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
  3. The text references files that are not there: add them or drop the references.
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 · 6

  • high Exfiltration intent-browser-credential-store references/po-token-setup.md:163
    Accesses a browser credential / cookie store
    yt-dlp --cookies-from-browser chrome "VIDEO_URL"
  • high Exfiltration intent-browser-credential-store SKILL.md:186
    Accesses a browser credential / cookie store
    yt-dlp --cookies-from-browser chrome -f "bestvideo[height<=1080]+bestaudio/best" "VIDEO_URL"
Medium and low: 4
  • medium Exfiltration intent-browser-credential-store SKILL.md:413
    Accesses a browser credential / cookie store (quoted — discussed, not commanded)
    **Symptom**: `Extracting cookies from chrome` hangs indefinitely.
    quoted
  • low Exfiltration intent-browser-credential-store scripts/download_video.py:747
    Accesses a browser credential / cookie store (security demo / example; quoted — discussed, not commanded)
    cookies_from_browser: Load cookies from browser (e.g., chrome, firefox)
    demoquoted
  • low Exfiltration intent-browser-credential-store scripts/download_video.py:988
    Accesses a browser credential / cookie store (security demo / example; quoted — discussed, not commanded)
    help="Load cookies from browser (e.g., chrome, firefox)",
    demoquoted
  • low Exfiltration intent-browser-credential-store SKILL.md:297
    Accesses a browser credential / cookie store (security demo / example; quoted — discussed, not commanded)
    - `--cookies-from-browser` - Load cookies from a browser (e.g., chrome, firefox)
    demoquoted

Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 5009 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: URL
  • warning missing-ref reference to a missing file: THUMBNAIL_URL

Process rating: all ten parameters 57/100

Will not run. References files that are not bundled: URL, THUMBNAIL_URL
  • 0Tools and files. 2 referenced file(s) missing: URL, THUMBNAIL_URL
  • 0Result and completion. Does not say what the result is
  • 70When it triggers. States when to use, but not when not to
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 70Execution cost. Instruction body is 5009 tokens
  • 85Steps. 109 steps, 2 vague phrases
  • 100Failures and branches. 4 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Running it twice. Mutating operations check current state
  • 100Progress reporting. Reports progress
  • low 16 top-level sections: this looks like several domains in one skill

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

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Output format is not stated: the model decides each time
  • -2localhost URLs: will not work for another user
  • +1No license
  • +2Single-language instructions
  • +3Description length 370: enough signal without eating the budget
  • +4Structure: 46 headings
  • +3Step-by-step instructions: 109 items
  • +4Has examples (21 code blocks)
  • +4Reference files are cited in the instructions (3 of 3)
  • +3All 1 scripts are documented

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