SKILLEMALL.ai
GitHub ↗ RU Sign in

BB bilibili-ai-subtitle

Download Bilibili AI-generated subtitles (auto-subtitles) for videos. Use when you need to quickly get subtitles from Bilibili videos that have AI-generated captions. Supports 9 languages: Chinese, English, Japanese, Spanish, Arabic, Portuguese, Korean, German, French. Language priority can be customized.

Not recommendedcritical or high security findings
ClawHub Agent Skills author: 54Lynnn v2.0.0 MIT-0 3 files · 1 script body ≈ 738 tokens Open the sourceclawhub.ai↗ analyzed 4 d ago

As a process B 69/100 · Nearly there — weak spots: when it triggers, failures and branches, running it twice

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
B
79/100
safety, quality, tests
Safety 60%
72
Quality 40%
90
Run on models
none yet
Process rating
B
69/100
Nearly there
Failures and branches w 10
0
When it triggers w 12
20
Running it twice w 4
30
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 · 3

  • high Exfiltration intent-browser-credential-store scripts/bilibili_ai_subtitle.sh:134
    Accesses a browser credential / cookie store
    TEST=$(yt-dlp --list-subs --cookies-from-browser "chromium:$CHROMIUM_PATH" "$VIDEO_URL" 2>&1 | head -1)
Medium and low: 2
  • medium Exfiltration intent-browser-credential-store scripts/bilibili_ai_subtitle.sh:137
    Accesses a browser credential / cookie store (quoted — discussed, not commanded)
    COOKIE_PARAM="--cookies-from-browser chromium:$CHROMIUM_PATH"
    quoted
  • medium Exfiltration intent-browser-credential-store scripts/bilibili_ai_subtitle.sh:149
    Accesses a browser credential / cookie store (quoted — discussed, not commanded)
    COOKIE_PARAM="--cookies-from-browser edge:C:/Users/$WIN_USER/AppData/Local/Microsoft/Edge/User Data"
    quoted

Files scanned: 3. 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 69/100

  • 0Failures and branches. Linear process with no failure handling
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 1 mutating operations with no state check
  • 60Result and completion. Output format stated, no completion criterion
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 100Tools and files. No external tools needed
  • 100Steps. 13 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 738 tokens
  • 100Progress reporting. Reports progress

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)
  • +1No license
  • +2Single-language instructions
  • +3Description length 306: enough signal without eating the budget
  • +4Structure: 12 headings
  • +3Step-by-step instructions: 13 items
  • +3Output format is stated explicitly
  • +4Has examples (3 code blocks)
  • +3All 1 scripts are documented

Quality base 70; lint remarks subtract, signals add up to 100. Result: 90.

External checks

ClawHub: suspicious
This subtitle downloader is mostly aligned with its purpose, but it automatically uses local browser login cookies without a clear opt-in warning.
LLM: suspicious (high) · VirusTotal: · 29 May 2026