SKILLEMALL.ai
GitHub ↗ RU Sign in

FB youtube-acquisition

yt-dlp patterns for acquiring content from YouTube and video platforms

Not recommendedcritical or high security findings · low grade F
jmagly/aiwg Agent Skills author: jmagly 1 file body ≈ 6 249 tokens Open the sourcegithub.com↗ analyzed 9 h ago

yt-dlp patterns for acquiring content from YouTube and video platforms

As a process B 66/100 · Nearly there — weak spots: when it triggers, progress reporting

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
F
49/100
safety, quality, tests
Safety 60%
41
Quality 40%
61
Run on models
none yet
Process rating
B
66/100
Nearly there
Progress reporting w 2
0
When it triggers w 12
20
Failures and branches w 10
50
the three weakest of ten parameters · all ten
This is a copy of a skill from another catalog; the rating counts the canonical one: youtube-acquisition (jmagly/aiwg)

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. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  3. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
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 · 4

  • high Exfiltration intent-browser-credential-store SKILL.md:611
    Accesses a browser credential / cookie store
    yt-dlp --cookies-from-browser chrome --cookies cookies.txt "VIDEO_URL"
  • high Exfiltration intent-browser-credential-store SKILL.md:620
    Accesses a browser credential / cookie store
    yt-dlp --cookies-from-browser "chromium:$HOME/.var/app/org.chromium.Chromium/config/chromium" "VIDEO_URL"
  • high Exfiltration intent-browser-credential-store SKILL.md:623
    Accesses a browser credential / cookie store
    yt-dlp --cookies-from-browser "chromium:$HOME/.var/app/io.github.ungoogled_software.ungoogled_chromium/config/chromium" "VIDEO_URL"
Medium and low: 1
  • medium Exfiltration intent-browser-credential-store SKILL.md:616
    Accesses a browser credential / cookie store (quoted — discussed, not commanded)
    `--cookies-from-browser chromium` does NOT find Flatpak Chromium installs (or any other Flatpak browser) — the binary's default profile path doesn't match the Flatpak sandbox layout. Pass an explicit
    quoted

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

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • warning body-long SKILL.md body ≈ 6249 tokens (recommended < 5000); move details to references/
  • note frontmatter-key unknown frontmatter key "namespace"
  • note edit-residue the text marks something as outdated (lines 99, 765): check that old rules are not kept next to new ones — the full check reads the text for contradictions

Process rating: all ten parameters 66/100

  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 50Failures and branches. 0 branches, has a failure section
  • 60Tools and files. Uses tools (python) that frontmatter does not declare
  • 60Result and completion. Output format stated, no completion criterion
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 70Execution cost. Instruction body is 6249 tokens
  • 100Steps. 33 steps
  • 100Consistency. Name and required fields are in place
  • 100Running it twice. No mutating operations
  • low 23 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)
  • +3Description length 70: 120–800 characters recommended
  • +1No license
  • +2Single-language instructions
  • +4Structure: 82 headings
  • +3Step-by-step instructions: 33 items
  • +3Output format is stated explicitly
  • +4Has examples (57 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 61.