SKILLEMALL.ai
GitHub ↗ RU Sign in

CF clawmobile

ClawMobile - 完整的 Android 自动化工具包，深度集成 AutoX.js。 提供工作流管理、任务录制、AI 智能干预、会员系统、HTTP API 通信等完整功能。 支持自动化测试、RPA 流程自动化、移动应用交互等场景。 适用场景：自动化测试、批量操作、流程录制和回放、无人值守任务、移动应用 RPA。

ClawHub Agent Skills author: sundayplus v1.0.0 MIT-0 15 files · 3 scripts body ≈ 4 351 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process F 31/100 · Will not run — References files that are not bundled: LICENSE

IntegrationInfrastructuretype 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
C
68/100
safety, quality, tests
Safety 60%
75
Quality 40%
58
Run on models
none yet
Process rating
F
31/100
Will not run
References files that are not bundled: LICENSE
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

The same skill appears in 1 more place: ClawHub

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Dangerous commands medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

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.

Exfiltration medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

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. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  2. 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 · 5

✓ No critical or high findings

Medium and low: 5
  • medium Dangerous commands cmd-shell-rc SKILL.md:402
    Writes to a shell startup file
    echo 'export CLAWMOBILE_API_URL="http://loca…765"' >> ~/.bashrc
  • medium Dangerous commands cmd-shell-rc SKILL.md:403
    Writes to a shell startup file
    echo 'export CLAWMOBILE_API_TOKEN="your-autox-token-here"' >> ~/.bashrc
  • medium Exfiltration net-credential-use SKILL.md:476
    Credential used in a network call (verify the destination is the intended service)
    curl -H "Authorization: Bearer $TOKEN" \
  • medium Exfiltration net-credential-use SKILL.md:480
    Credential used in a network call (verify the destination is the intended service)
    curl -X POST -H "Authorization: Bearer $TOKEN" \
  • medium Exfiltration net-credential-use SKILL.md:486
    Credential used in a network call (verify the destination is the intended service)
    curl -X POST -H "Authorization: Bearer $TOKEN" \

Files scanned: 15. 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 missing-ref reference to a missing file: LICENSE
  • note frontmatter-key unknown frontmatter key "email"
  • note frontmatter-key unknown frontmatter key "repository"

Process rating: all ten parameters 31/100

Will not run. References files that are not bundled: LICENSE
  • 0Tools and files. 1 referenced file(s) missing: LICENSE
  • 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
  • 30Running it twice. 3 mutating operations with no state check
  • 70Execution cost. Instruction body is 4351 tokens
  • 100Steps. 148 steps
  • 100Consistency. Name and required fields are in place

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
  • -2localhost URLs: will not work for another user
  • -269 emoji in the instructions: noise for the model
  • -33 of 3 scripts are never mentioned in SKILL.md
  • +2Single-language instructions
  • +3Description length 160: enough signal without eating the budget
  • +4Structure: 60 headings
  • +3Step-by-step instructions: 148 items
  • +4Has examples (43 code blocks)
  • +1License stated

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

External checks

ClawHub: suspicious
This Android automation skill is mostly coherent, but it needs Review because it can remotely control a device while shipping weak default authentication and broad network settings.
LLM: suspicious (high) · VirusTotal: · 29 May 2026