SKILLEMALL.ai
GitHub ↗ RU Sign in

DF local-webapp-delivery

在 WorkBuddy（Windows）环境里交付零依赖本地 Web 应用，并绕开官方测试技能完全不覆盖的本机专属坑。当用户要在本机跑起来一个本地 Web 应用 / 单文件工具 / 案例库 / 看板 / 小工具，或要验证刚写完的 HTML/JS/Python 交付物真的能工作时使用。独家覆盖：Bash 缺 coreutils、bash 是 WSL 启动桩、rm 是坏 shim、PowerShell 不回显 stdout、cwd 漂移、预览面板靠 HEAD 探活——这些在干净 Linux 环境里遇不到。

Not recommendedcritical or high security findings · low grade D
ClawHub Agent Skills author: robin v1.0.0 MIT-0 2 files body ≈ 7 297 tokens Open the sourceclawhub.ai↗ analyzed 14 d ago

在 WorkBuddy（Windows）环境里交付零依赖本地 Web 应用，并绕开官方测试技能完全不覆盖的本机专属坑。当用户要在本机跑起来一个本地 Web 应用 / 单文件工具 / 案例库 / 看板 / 小工具，或要验证刚写完的 HTML/JS/Python 交付物真的能工作时使用。独家覆盖：Bash 缺…

As a process F 33/100 · No process to follow — References files that are not bundled: scripts/test_*.py

ProcedureGitHubSoftware 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
68/100
safety, quality, tests
Safety 60%
82
Quality 40%
47
Run on models
none yet
Process rating
F
33/100
No process to follow
References files that are not bundled: scripts/test_*.py
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. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  3. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
  4. 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 · 1

  • high Exfiltration exfil-read-secret-files SKILL.md:480
    Reads credential / secret files
    m = re.search(r'https?://([^:]+):([^@]+)@github\.com', open(os.path.expanduser('~/.git-credentials')).read())

Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • warning body-long SKILL.md body ≈ 7297 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: scripts/test_*.py
  • note frontmatter-key unknown frontmatter key "slug"
  • note frontmatter-key unknown frontmatter key "displayName"
  • note frontmatter-key unknown frontmatter key "visibility"
  • note frontmatter-key unknown frontmatter key "subCategories"
  • note frontmatter-key unknown frontmatter key "agent_created"

Process rating: all ten parameters 33/100

Will not run. References files that are not bundled: scripts/test_*.py
  • 0Tools and files. 1 referenced file(s) missing: scripts/test_*.py
  • 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
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 18 mutating operations with no state check
  • 70Execution cost. Instruction body is 7297 tokens
  • 100Steps. 66 steps
  • 100Consistency. Name and required fields are in place
  • 100Progress reporting. Reports progress
  • low 13 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (11 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
  • -4Absolute local paths (C:\Users, /home/…): not portable
  • -2localhost URLs: will not work for another user
  • +1No license
  • +2Single-language instructions
  • +3Description length 253: enough signal without eating the budget
  • +4Structure: 45 headings
  • +3Step-by-step instructions: 66 items
  • +4Has examples (42 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 47.

External checks

ClawHub: suspicious
The skill is mostly a local web app delivery guide, but it also tells an agent to read stored GitHub credentials and use them for repository creation and pushes.
LLM: suspicious (high) · 20 Sept 2026