SKILLEMALL.ai
RU Sign in

FD youtube-content

YouTube视频转录与内容提取：字幕优先、Whisper兜底、批量处理、结构化笔记

Not recommendedcritical or high security findings · low grade F
ClawHub Agent Skills author: Miles v1.0.0 MIT-0 6 files body ≈ 1 248 tokens Open the sourceclawhub.ai↗ analyzed 24 h ago

YouTube视频转录与内容提取：字幕优先、Whisper兜底、批量处理、结构化笔记

As a process D 46/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

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
F
34/100
safety, quality, tests
Safety 60%
0
Quality 40%
86
Run on models
none yet
Process rating
D
46/100
Unfinished process
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
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.
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 · 7

  • high Exfiltration intent-browser-credential-store references/whisper-transcription.md:150
    Accesses a browser credential / cookie store
    无 cookies 绕过方案。`--cookies-from-browser chrome` 是唯一可靠方法。
  • high Exfiltration intent-browser-credential-store references/whisper-transcription.md:152
    Accesses a browser credential / cookie store
    **Chrome cookie 解密可能静默失败**（返回 0 cookies）。验证 Chrome 已登录 YouTube。
  • high Exfiltration intent-browser-credential-store SKILL.md:44
    Accesses a browser credential / cookie store
    /opt/homebrew/Caskroom/miniconda/base/bin/yt-dlp --cookies-from-browser chrome \
  • high Exfiltration intent-browser-credential-store SKILL.md:48
    Accesses a browser credential / cookie store
    /opt/homebrew/Caskroom/miniconda/base/bin/yt-dlp --cookies-from-browser chrome \
  • high Exfiltration intent-browser-credential-store SKILL.md:55
    Accesses a browser credential / cookie store
    /opt/homebrew/Caskroom/miniconda/base/bin/yt-dlp --cookies-from-browser chrome \
  • high Exfiltration intent-browser-credential-store SKILL.md:211
    Accesses a browser credential / cookie store
    - **Chrome cookies**：`--cookies-from-browser chrome` 可能静默返回 0 cookies（解密失败），需检查
Medium and low: 1
  • medium Exfiltration intent-browser-credential-store references/whisper-transcription.md:147
    Accesses a browser credential / cookie store (quoted — discussed, not commanded)
    修复：conda yt-dlp + `--cookies-from-browser chrome` + `--remote-components ejs:github`
    quoted

Files scanned: 6. 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 46/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Failures and branches. Linear process with no failure handling
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 60Tools and files. Uses tools (python) that frontmatter does not declare
  • 100Steps. 15 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 1248 tokens
  • 100Running it twice. No mutating operations

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 42: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • -2localhost URLs: will not work for another user
  • +1No license
  • +2Single-language instructions
  • +4Structure: 24 headings
  • +3Step-by-step instructions: 15 items
  • +4Has examples (11 code blocks)
  • +4Reference files are cited in the instructions (2 of 2)
  • +3All 2 scripts are documented

Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.

External checks

ClawHub: suspicious
The skill is purpose-built for YouTube transcription, but its default workflow uses Chrome browser cookies for yt-dlp without an explicit consent gate.
LLM: suspicious (high) · VirusTotal: · 31 May 2026