SKILLEMALL.ai
GitHub ↗ RU Sign in

DD 虾BB

免费 macOS 语音转文字，专为 Vibe Coding 设计。按住 Globe 键说话，文字自动出现在光标位置。支持智能模式：翻译、Prompt 优化、邮件生成。Powered by Google Gemini。

Not recommendedcritical or high security findings · low grade D
ClawHub Agent Skills author: dyz2102 v1.3.2 MIT-0 30 files · 4 scripts body ≈ 270 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process D 49/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

ProcedureInfrastructureAI and agentsSoftware developmenttype 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
57/100
safety, quality, tests
Safety 60%
56
Quality 40%
58
Run on models
none yet
Process rating
D
49/100
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.

Dangerous commands
If you install

The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

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.
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 Dangerous commands cmd-persistence uninstall.sh:8
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    launchctl unload ~/Library/LaunchAgents/com.xiabb.plist 2>/dev/null
  • high Dangerous commands cmd-persistence uninstall.sh:9
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    rm -f ~/Library/LaunchAgents/com.xiabb.plist
Medium and low: 4
  • medium Dangerous commands cmd-persistence install.sh:168
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
    PLIST_PATH="$HOME/Library/LaunchAgents/$BUNDLE_ID.plist"
    code literal
  • low Obfuscation obf-base64-blob design-versions/v2-coral-sketchy/stitch-landing-page/src/App.tsx:97
    Long base64-looking blob (quoted — discussed, not commanded)
    src="https://lh3.…com/aida-public/AB6A…QSL
    quoted
  • low Obfuscation obf-base64-blob design-versions/v2-coral-sketchy/stitch-landing-page/src/App.tsx:132
    Long base64-looking blob (quoted — discussed, not commanded)
    src="https://lh3.…com/aida-public/AB6A…i-1
    quoted
  • low Obfuscation obf-base64-blob design-versions/v2-coral-sketchy/stitch-landing-page/src/App.tsx:155
    Long base64-looking blob (quoted — discussed, not commanded)
    src="https://lh3.…com/aida-public/AB6A…Wm9
    quoted

Files scanned: 28. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning name-format name should be kebab-case (lowercase letters, digits, hyphens)
  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • note frontmatter-key unknown frontmatter key "homepage"
  • note frontmatter-key unknown frontmatter key "repository"

Process rating: all ten parameters 49/100

  • 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
  • 40Consistency. Frontmatter name (虾BB) differs from the folder (xiabb)
  • 100Tools and files. No external tools needed
  • 100Steps. 4 steps
  • 100Execution cost. Instruction body is 270 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 108: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • -214 emoji in the instructions: noise for the model
  • -31 of 1 scripts are never mentioned in SKILL.md
  • +2Single-language instructions
  • +4Structure: 5 headings
  • +3Step-by-step instructions: 4 items
  • +4Has examples (1 code blocks)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 58.

External checks

ClawHub: suspicious
This appears to be a real macOS dictation tool, but it needs Review because it combines microphone capture, cloud transcription, Accessibility control, auto-paste, local API-key storage, and under-disclosed install/persistence behavior.
LLM: suspicious (high) · VirusTotal: · 29 May 2026