SKILLEMALL.ai
GitHub ↗ RU Sign in

DD youtube-to-chinese

将 YouTube 视频转成中文稿，包含完整中文转录、内容摘要和核心亮点。当用户提供 YouTube 链接并要求转录、翻译、生成中文稿、摘要或笔记时触发。Trigger phrases: YouTube转中文, 视频转文字, 转录视频, 生成中文笔记, 视频摘要, youtube transcript chinese.

Not recommendedcritical or high security findings · low grade D
ClawHub Agent Skills author: 古 晖 v1.0.0 MIT-0 3 files · 1 script body ≈ 333 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

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
D
44/100
safety, quality, tests
Safety 60%
22
Quality 40%
77
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 · 6

  • high Exfiltration intent-browser-credential-store skill-card.md:30
    Accesses a browser credential / cookie store
    - [Get cookies.txt LOCALLY Chrome extension](https://chrome.google.com/webstore/detail/get-cookiestxt-locally) <br>
  • high Exfiltration intent-browser-credential-store SKILL.md:21
    Accesses a browser credential / cookie store
    - 第 3 参数传 cookies 文件路径（`/path/to/cookies.txt`）或 `browser:chrome`（从 Chrome 读取 cookies）
  • high Exfiltration intent-browser-credential-store SKILL.md:69
    Accesses a browser credential / cookie store
    2. 用浏览器 cookies：在第 3 参数传 `browser:chrome`（需在有 YouTube 登录状态的机器上运行）
  • high Exfiltration intent-browser-credential-store SKILL.md:70
    Accesses a browser credential / cookie store
    3. 导出 cookies 文件：在 Chrome 安装 [Get cookies.txt LOCALLY](https://chrome.google.com/webstore/detail/get-cookiestxt-locally) 扩展，导出后传路径
Medium and low: 2
  • medium Exfiltration intent-browser-credential-store scripts/download_audio.sh:55
    Accesses a browser credential / cookie store (detector / deny-list definition)
    echo "  1. Export cookies: yt-dlp --cookies-from-browser chrome ..." >&2
    detector
  • low Exfiltration intent-browser-credential-store scripts/download_audio.sh:39
    Accesses a browser credential / cookie store (code comment; security demo / example)
    # e.g. COOKIES="browser:chrome"
    commentdemo

Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning frontmatter-yaml SKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 2, column 14: description: 将 YouTube 视频转成中文稿，包含完整中文转录、内容摘要和核心亮点。当用户提供 YouTube 链接并要求转录、翻译、生成中文… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value

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 (web) that frontmatter does not declare
  • 100Steps. 11 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 333 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)
  • +3Output format is not stated: the model decides each time
  • +1No license
  • +2Single-language instructions
  • +3Description length 160: enough signal without eating the budget
  • +4Structure: 9 headings
  • +3Step-by-step instructions: 11 items
  • +4Has examples (2 code blocks)
  • +3All 1 scripts are documented

Quality base 70; lint remarks subtract, signals add up to 100. Result: 77.

External checks

ClawHub: suspicious
The skill matches its YouTube transcription purpose, but it can read Chrome login cookies for YouTube without clearly warning users that those are sensitive session credentials.
LLM: suspicious (high) · VirusTotal: · 29 May 2026