SKILLEMALL.ai
GitHub ↗ RU Sign in

CF video-learning-notes

Use this skill when the user provides a video URL and wants a complete Markdown learning note. It downloads the original video, transcribes audio with qwen-audio/STT, extracts timestamped frames with ffmpeg, reads and filters key screenshots one by one in combination with subtitles, and finally generates an illustrated learning note.

Not recommendedcritical or high security findings
ClawHub Agent Skills author: noah v1.0.2 MIT-0 4 files body ≈ 2 454 tokens Open the sourceclawhub.ai↗ analyzed 4 d ago

As a process F 49/100 · Will not run — References files that are not bundled: relative/path/to/video.mp4, selected_frames/frame_000003__00-01-30.jpg

GeneratorMedia 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
73/100
safety, quality, tests
Safety 60%
72
Quality 40%
74
Run on models
none yet
Process rating
F
49/100
Will not run
References files that are not bundled: relative/path/to/video.mp4, selected_frames/frame_000003__00-01-30.jpg
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
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 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 · 3

  • high Exfiltration intent-browser-credential-store SKILL.md:46
    Accesses a browser credential / cookie store
    yt-dlp -P "/path/to/workspace" --cookies-from-browser chrome -o "%(title)s.%(ext)s" "YOUTUBE_URL"
Medium and low: 2
  • medium Exfiltration intent-browser-credential-store SKILL.md:54
    Accesses a browser credential / cookie store (quoted — discussed, not commanded)
    - YouTube / YouTube Music: use `--cookies-from-browser chrome` by default. Supported browser cookie sources include `chrome`, `firefox`, `safari`, `edge`, `brave`, and `opera`.
    quoted
  • medium Exfiltration intent-browser-credential-store SKILL.md:63
    Accesses a browser credential / cookie store (detector / deny-list definition)
    - `HTTP 403 Forbidden`: retry with `--cookies-from-browser chrome` or another browser where the user is logged in.
    detector

Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning missing-ref reference to a missing file: relative/path/to/video.mp4
  • warning missing-ref reference to a missing file: selected_frames/frame_000003__00-01-30.jpg

Process rating: all ten parameters 49/100

Will not run. References files that are not bundled: relative/path/to/video.mp4, selected_frames/frame_000003__00-01-30.jpg
  • 0Tools and files. 2 referenced file(s) missing: relative/path/to/video.mp4, selected_frames/frame_000003__00-01-30.jpg
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 30Running it twice. 5 mutating operations with no state check
  • 70When it triggers. States when to use, but not when not to
  • 100Steps. 43 steps
  • 100Failures and branches. 8 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 2454 tokens
  • low The response is described with custom markup (5 tags): a typed call is more reliable

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
  • -41 reference files, but SKILL.md never points to them: the model will not open them
  • +1No license
  • +2Single-language instructions
  • +3Description length 335: enough signal without eating the budget
  • +4Structure: 12 headings
  • +3Step-by-step instructions: 43 items
  • +4Has examples (5 code blocks)
  • +3All 1 scripts are documented

Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.

External checks

ClawHub: suspicious
The skill’s video-note workflow is mostly coherent, but it defaults to reading local browser cookies for YouTube downloads, which should require explicit user approval.
LLM: suspicious (high) · 28 May 2026