SKILLEMALL.ai
GitHub ↗ RU Sign in

FC openclaw-omni-expert

OpenClaw全能专家系统；支持多种远程软件(UU/RustDesk/ToDesk/向日葵/RDP)、一键安装、TOP3专家诊断、全自动驾驶、Agent/Workflow编排、工具链配置、记忆系统、插件开发、监控运维、100+实战案例库和故障排查手册；用户说"安装 OpenClaw"、"配置 OpenClaw"、"诊断 OpenClaw 问题"、"创建 Agent"、"编排 Workflow"、"远程控制电脑"、"用鼠标操作"时使用

Not recommendedcritical or high security findings · low grade F
ClawHub Agent Skills author: thinkbugs v1.0.0 MIT-0 40 files · 1 script body ≈ 1 798 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process C 53/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

ProcedureAI and agentsSoftware developmentInfrastructuretype 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
F
28/100
safety, quality, tests
Safety 60%
0
Quality 40%
69
Run on models
none yet
Process rating
C
53/100
Has gaps
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.

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. 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 · 32

  • high Dangerous commands cmd-pipe-to-shell references/desktop-remote-guide.md:462
    Downloads and executes remote code from an unrecognised host (pipe to shell)
    curl -fsSL https://rpm.nodesource.com/setup_22.x | sudo bash -
  • high Dangerous commands cmd-disable-security references/troubleshooting-guide.md:714
    Disables a security control (Defender, Gatekeeper, SIP, firewall, execution policy)
    Add-MpPreference -ExclusionPath "$env:USERPROFILE\.openclaw"
  • high Dangerous commands cmd-disable-security references/troubleshooting-guide.md:717
    Disables a security control (Defender, Gatekeeper, SIP, firewall, execution policy)
    Add-MpPreference -ExclusionPath "$env:USERPROFILE\.npm-global"
Medium and low: 29
  • medium Exfiltration exfil-webhook-url references/monitoring-guide.md:215
    Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)
    "webhook_url": "https://hooks.slack.com/services/xxx"
    quoted
  • medium Exfiltration exfil-webhook-url references/monitoring-guide.md:245
    Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)
    "webhook_url": "https://hooks.slack.com/services/xxx",
    quoted
  • medium Dangerous commands cmd-pipe-to-shell-known-host references/troubleshooting-guide.md:40
    Pipe-to-shell installer from a well-known host (still executes remote code)
    curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.39.7/install.sh | bash
  • medium Dangerous commands cmd-privilege references/troubleshooting-guide.md:77
    Privilege escalation / world-writable permissions
    sudo chown -R $(whoami) $(npm config get prefix)/lib/node_modules
  • medium Dangerous commands cmd-privilege references/troubleshooting-guide.md:78
    Privilege escalation / world-writable permissions
    sudo chown -R $(whoami) $(npm config get prefix)/bin
  • medium Dangerous commands cmd-shell-rc references/troubleshooting-guide.md:90
    Writes to a shell startup file
    echo 'export PATH=~/.npm-global/bin:$PATH' >> ~/.bashrc  # 或 ~/.zshrc
  • medium Dangerous commands cmd-pipe-to-shell references/troubleshooting-guide.md:100
    Downloads and executes remote code from an unrecognised host (pipe to shell) (the skill's own vendor host)
    curl -fsSL https://openclaw.ai/install.sh | bash
    vendor-host
  • medium Dangerous commands cmd-shell-rc references/troubleshooting-guide.md:209
    Writes to a shell startup file
    echo 'export PATH=$(npm config get prefix)/bin:$PATH' >> ~/.bashrc
  • medium Dangerous commands cmd-execpolicy-bypass references/troubleshooting-guide.md:630
    Runs PowerShell with execution policy bypassed
    Set-ExecutionPolicy -Scope Process -ExecutionPolicy Bypass
  • medium Dangerous commands cmd-execpolicy-bypass references/troubleshooting-guide.md:641
    Runs PowerShell with execution policy bypassed
    powershell -ExecutionPolicy Bypass -File inst…ps1
  • medium Dangerous commands cmd-pipe-to-shell-known-host references/troubleshooting.md:37
    Pipe-to-shell installer from a well-known host (still executes remote code)
    curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.39.0/install.sh | bash
  • medium Dangerous commands cmd-shell-rc references/troubleshooting.md:62
    Writes to a shell startup file
    echo 'export PATH=~/.npm-global/bin:$PATH' >> ~/.bashrc
  • medium Dangerous commands cmd-pipe-to-shell scripts/config_expert.py:136
    Downloads and executes remote code from an unrecognised host (pipe to shell) (string literal in code, not executed)
    "step1": "安装 Ollama: curl -fsSL https://ollama.com/install.sh | sh",
    code literal
  • medium Dangerous commands cmd-pipe-to-shell scripts/desktop-remote-helper.py:504
    Downloads and executes remote code from an unrecognised host (pipe to shell) (string literal in code, not executed)
    curl -fsSL https://rpm.nodesource.com/setup_22.x | sudo bash -
    code literal
  • medium Dangerous commands cmd-pipe-to-shell-known-host scripts/install_openclaw.sh:110
    Pipe-to-shell installer from a well-known host (still executes remote code)
    curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.39.7/install.sh | bash
  • medium Dangerous commands cmd-privilege scripts/install_openclaw.sh:235
    Privilege escalation / world-writable permissions
    sudo chown -R $(whoami) "$npm_global/lib/node_modules"
  • medium Dangerous commands cmd-privilege scripts/install_openclaw.sh:236
    Privilege escalation / world-writable permissions
    sudo chown -R $(whoami) "$npm_global/bin"
  • medium Exfiltration exfil-webhook-url scripts/monitoring_expert.py:486
    Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)
    "webhook_url": "https://hooks.slack.com/services/xxx",
    quoted
  • low Dangerous commands cmd-privilege references/desktop-remote-guide.md:462
    Privilege escalation / world-writable permissions (detector / deny-list definition)
    curl -fsSL https://rpm.nodesource.com/setup_22.x | sudo bash -
    detector
  • low Dangerous commands cmd-cron-mention references/troubleshooting-guide.md:959
    Mentions editing / listing crontab
    crontab -e
  • low Dangerous commands cmd-pipe-to-shell-known-host scripts/autopilot.py:519
    Pipe-to-shell installer from a well-known host (still executes remote code) (string literal in code, not executed)
    curl -fsSL https://deb.nodesource.com/setup_22.x | bash -
    code literal
  • low Dangerous commands cmd-privilege scripts/desktop-remote-helper.py:504
    Privilege escalation / world-writable permissions (detector / deny-list definition; string literal in code, not executed)
    curl -fsSL https://rpm.nodesource.com/setup_22.x | sudo bash -
    detectorcode literal
  • low Dangerous commands cmd-background-process scripts/desktop-remote-helper.py:652
    Starts a background / autostarted process (string literal in code, not executed)
    sudo systemctl enable openclaw-gateway
    code literal
  • low Dangerous commands cmd-pipe-to-shell-known-host scripts/env_check.py:447
    Pipe-to-shell installer from a well-known host (still executes remote code) (string literal in code, not executed)
    "curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.39.7/install.sh | bash",
    code literal
  • low Dangerous commands cmd-pipe-to-shell-known-host scripts/fix_issues.py:111
    Pipe-to-shell installer from a well-known host (still executes remote code) (string literal in code, not executed)
    "curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.39.7/install.sh | bash",
    code literal
  • low Dangerous commands cmd-pipe-to-shell-known-host scripts/remote_executor.py:159
    Pipe-to-shell installer from a well-known host (still executes remote code) (string literal in code, not executed)
    curl -fsSL https://deb.nodesource.com/setup_22.x | bash -
    code literal
  • low Dangerous commands cmd-execpolicy-bypass scripts/remote-helper.py:260
    Runs PowerShell with execution policy bypassed (quoted — discussed, not commanded)
    command = f"powershell -ExecutionPolicy Bypass -File {remote_script}"
    quoted
  • low Dangerous commands cmd-pipe-to-shell-known-host scripts/troubleshooting.py:73
    Pipe-to-shell installer from a well-known host (still executes remote code) (string literal in code, not executed)
    "安装 nvm: curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.39.0/install.sh | bash",
    code literal
  • low Dangerous commands cmd-shell-rc scripts/troubleshooting.py:112
    Writes to a shell startup file (string literal in code, not executed)
    "添加到 PATH: echo 'export PATH=~/.npm-global/bin:$PATH' >> ~/.bashrc",
    code literal

Files scanned: 40. 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")
  • note frontmatter-key unknown frontmatter key "dependency"

Process rating: all ten parameters 53/100

  • 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
  • 100Tools and files. No external tools needed
  • 100Steps. 9 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 1798 tokens
  • 100Running it twice. No mutating operations
  • low 12 top-level sections: this looks like several domains in one skill

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

  • +4Description does not say when NOT to use the skill (false activations)
  • +3Output format is not stated: the model decides each time
  • -413 reference files, but SKILL.md never points to them: the model will not open them
  • -311 of 25 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +5Description quotes 6 example trigger phrases
  • +3Description length 219: enough signal without eating the budget
  • +4Structure: 31 headings
  • +3Step-by-step instructions: 9 items
  • +4Has examples (18 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 69.

External checks

ClawHub: suspicious
This is a powerful remote-control and auto-repair skill whose core purpose is disclosed, but it gives agents broad unattended authority to change local or remote computers.
LLM: suspicious (high) · VirusTotal: · 29 May 2026