SKILLEMALL.ai
GitHub ↗ RU Sign in

FD openclaw-two-way-deployment

(no description)

Not recommendedcritical or high security findings · low grade F
ClawHub Agent Skills author: MarsHong-86 v1.0.0 MIT-0 7 files · 4 scripts body ≈ 10 273 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process D 44/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

ProcedureInfrastructuretype 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
0/100
safety, quality, tests
Safety 60%
0
Quality 40%
0
Run on models
none yet
Process rating
D
44/100
Unfinished process
Result and completion w 14
0
When it triggers w 12
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.

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. Add a description to the frontmatter: without it the skill never triggers.
  3. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
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 · 31

  • high Dangerous commands cmd-pipe-to-shell plan1-cloud-gateway.sh:142
    Downloads and executes remote code from an unrecognised host (pipe to shell)
    curl -fsSL https://rpm.nodesource.com/setup_22.x | bash -
  • high Dangerous commands cmd-pipe-to-shell SKILL.md:210
    Downloads and executes remote code from an unrecognised host (pipe to shell)
    curl -fsSL https://rpm.nodesource.com/setup_22.x | bash -
  • high Dangerous commands cmd-persistence SKILL.md:439
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    schtasks /Create /TN $TaskName /TR "powershell.exe $argument" /SC ONLOGON /RU SYSTEM /F 2>$null
  • high Dangerous commands cmd-persistence SKILL.md:445
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    schtasks /Create /TN $TaskName /TR "powershell.exe $argument" /SC ONLOGON /F 2>$null
  • high Dangerous commands cmd-persistence SKILL.md:1022
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    schtasks /Create /TN $TaskName /TR "powershell.exe $argument" /SC ONLOGON /F 2>$null
Medium and low: 26
  • medium Dangerous commands cmd-pipe-to-shell-known-host plan1-cloud-gateway.sh:44
    Pipe-to-shell installer from a well-known host (still executes remote code)
    curl -fsSL https://tailscale.com/install.sh | sh
  • medium Dangerous commands cmd-pipe-to-shell-known-host plan1-cloud-gateway.sh:139
    Pipe-to-shell installer from a well-known host (still executes remote code)
    curl -fsSL https://deb.nodesource.com/setup_22.x | bash -
  • medium Dangerous commands cmd-pipe-to-shell-known-host plan2-cloud-remote-gateway.sh:36
    Pipe-to-shell installer from a well-known host (still executes remote code)
    curl -fsSL https://tailscale.com/install.sh | sh
  • medium Dangerous commands cmd-pipe-to-shell-known-host plan2-cloud-remote-gateway.sh:76
    Pipe-to-shell installer from a well-known host (still executes remote code)
    curl -fsSL https://deb.nodesource.com/setup_22.x | bash -
  • medium Dangerous commands cmd-pipe-to-shell-known-host plan3-cloud-gateway.sh:29
    Pipe-to-shell installer from a well-known host (still executes remote code)
    curl -fsSL https://tailscale.com/install.sh | sh
  • medium Dangerous commands cmd-pipe-to-shell-known-host plan3-cloud-gateway.sh:54
    Pipe-to-shell installer from a well-known host (still executes remote code)
    curl -fsSL https://deb.nodesource.com/setup_22.x | bash -
  • medium Dangerous commands cmd-pipe-to-shell-known-host SKILL.md:112
    Pipe-to-shell installer from a well-known host (still executes remote code)
    curl -fsSL https://tailscale.com/install.sh | sh
  • medium Dangerous commands cmd-pipe-to-shell-known-host SKILL.md:207
    Pipe-to-shell installer from a well-known host (still executes remote code)
    curl -fsSL https://deb.nodesource.com/setup_22.x | bash -
  • medium Dangerous commands cmd-pipe-to-shell-known-host SKILL.md:586
    Pipe-to-shell installer from a well-known host (still executes remote code)
    curl -fsSL https://tailscale.com/install.sh | sh
  • medium Dangerous commands cmd-pipe-to-shell-known-host SKILL.md:626
    Pipe-to-shell installer from a well-known host (still executes remote code)
    curl -fsSL https://deb.nodesource.com/setup_22.x | bash -
  • medium Dangerous commands cmd-persistence SKILL.md:872
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (quoted — discussed, not commanded)
    Write-Host "     schtasks /Create /TN `"$TaskName`" /TR `"powershell -File '$startScript'`" /SC ONLOGON /F"
    quoted
  • medium Dangerous commands cmd-pipe-to-shell-known-host SKILL.md:1098
    Pipe-to-shell installer from a well-known host (still executes remote code)
    curl -fsSL https://tailscale.com/install.sh | sh
  • low Dangerous commands cmd-background-process plan1-cloud-gateway.sh:35
    Starts a background / autostarted process
    systemctl enable --now sshd 2>/dev/null || systemctl enable --now ssh 2>/dev/null || true
  • low Dangerous commands cmd-background-process plan1-cloud-gateway.sh:55
    Starts a background / autostarted process
    systemctl enable --now tailscaled 2>/dev/null || tailscaled &
  • low Dangerous commands cmd-background-process plan1-cloud-gateway.sh:218
    Starts a background / autostarted process
    systemctl enable openclaw-gateway
  • low Dangerous commands cmd-background-process plan2-cloud-remote-gateway.sh:43
    Starts a background / autostarted process
    systemctl enable --now tailscaled 2>/dev/null || tailscaled &
  • low Dangerous commands cmd-background-process plan2-cloud-remote-gateway.sh:155
    Starts a background / autostarted process
    systemctl enable openclaw-gateway
  • low Dangerous commands cmd-background-process plan3-cloud-gateway.sh:31
    Starts a background / autostarted process
    systemctl enable --now tailscaled 2>/dev/null || tailscaled &
  • low Dangerous commands cmd-background-process plan3-cloud-gateway.sh:117
    Starts a background / autostarted process
    systemctl enable openclaw-gateway
  • low Dangerous commands cmd-background-process SKILL.md:103
    Starts a background / autostarted process
    systemctl enable --now sshd 2>/dev/null || systemctl enable --now ssh 2>/dev/null || true
  • low Dangerous commands cmd-background-process SKILL.md:123
    Starts a background / autostarted process
    systemctl enable --now tailscaled 2>/dev/null || tailscaled &
  • low Dangerous commands cmd-background-process SKILL.md:286
    Starts a background / autostarted process
    systemctl enable openclaw-gateway
  • low Dangerous commands cmd-execpolicy-bypass SKILL.md:438
    Runs PowerShell with execution policy bypassed (detector / deny-list definition)
    $argument = "-ExecutionPolicy Bypass -WindowStyle Hidden -File `"$scriptPath`""
    detector
  • low Dangerous commands cmd-background-process SKILL.md:593
    Starts a background / autostarted process
    systemctl enable --now tailscaled 2>/dev/null || tailscaled &
  • low Dangerous commands cmd-background-process SKILL.md:702
    Starts a background / autostarted process
    systemctl enable openclaw-gateway
  • low Dangerous commands cmd-execpolicy-bypass SKILL.md:1020
    Runs PowerShell with execution policy bypassed (detector / deny-list definition)
    $argument = "-ExecutionPolicy Bypass -WindowStyle Hidden -File `"$startScript`""
    detector

Files scanned: 7. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • error frontmatter SKILL.md: no YAML frontmatter block found
  • error name-missing SKILL.md: frontmatter has no `name`
  • error description-missing SKILL.md: no `description` — the skill can never trigger
  • warning body-long SKILL.md body ≈ 10273 tokens (recommended < 5000); move details to references/

Process rating: all ten parameters 44/100

  • 0Result and completion. Does not say what the result is
  • 0When it triggers. No condition that starts the skill
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 30Running it twice. 6 mutating operations with no state check
  • 40Execution cost. Instruction body is 10273 tokens: crowds the task out of the window
  • 60Tools and files. Uses tools (bash, web, node) that frontmatter does not declare
  • 70Failures and branches. 24 branches
  • 100Steps. 4 steps
  • 100Consistency. Name and required fields are in place
  • low The response is described with custom markup (3 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)
  • +3Description length 0: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • -2localhost URLs: will not work for another user
  • -219 emoji in the instructions: noise for the model
  • +1No license
  • +2Single-language instructions
  • +4Structure: 57 headings
  • +3Step-by-step instructions: 4 items
  • +4Has examples (11 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 0.

External checks

ClawHub: suspicious
This skill mostly does what it says, but it installs persistent root-run network services and opens remote access in ways users should review carefully before use.
LLM: suspicious (high) · VirusTotal: · 29 May 2026