SKILLEMALL.ai
GitHub ↗ RU Sign in

DC gateway-resilience-guard

OpenClaw Gateway Resilience Guard keeps Gateway, channels, logs, and optional model-provider probes observable after Wi-Fi changes, WSL sleep/resume, session expiry, provider timeouts, or partial outages. It adds a localhost dashboard with charts, event trends, language/theme switching, strategy presets, guarded action unlock, native OpenClaw health probes, restart safeguards, systemd, LaunchAgent, Task Scheduler, and an optional OpenClaw plugin bridge.

Not recommendedcritical or high security findings · low grade D
ClawHub Agent Skills author: zc-kama v1.4.4 MIT-0 18 files · 6 scripts body ≈ 781 tokens Open the sourceclawhub.ai↗ analyzed 4 d ago

As a process C 63/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

IntegrationData and analyticsInfrastructuretype 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
55/100
safety, quality, tests
Safety 60%
47
Quality 40%
68
Run on models
none yet
Process rating
C
63/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
When it triggers w 12
20
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 · 15

  • high Dangerous commands cmd-persistence install-watchdog.ps1:94
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    Register-ScheduledTask -TaskName $TaskName -Action $Action -Trigger $Trigger -Settings $Settings -Principal $Principal -Description "External OpenClaw Gateway and channel resilience guard." | Out-Null
  • high Dangerous commands cmd-persistence install-watchdog.sh:264
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    launchctl bootstrap "gui/${uid}" "$PLIST_FILE"
Medium and low: 13
  • medium Dangerous commands cmd-persistence uninstall-watchdog.sh:12
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
    PLIST_FILE="${HOME}/Library/LaunchAgents/${PLIST_LABEL}.plist"
    code literal
  • low Dangerous commands cmd-background-process gateway-watchdog.sh:487
    Starts a background / autostarted process
    nohup "$python_bin" "${DASHBOARD_DIR}/server.py" >>"${STATE_DIR}/dashboard.log" 2>&1 &
  • low Dangerous commands cmd-execpolicy-bypass install-watchdog.ps1:85
    Runs PowerShell with execution policy bypassed (detector / deny-list definition; string literal in code, not executed)
    $Action = New-ScheduledTaskAction -Execute "powershell.exe" -Argument "-NoProfile -ExecutionPolicy Bypass -File `"$ScriptPath`" -ConfigPath `"$ConfigFile`""
    detectorcode literal
  • low Dangerous commands cmd-execpolicy-bypass install-watchdog.ps1:104
    Runs PowerShell with execution policy bypassed (quoted — discussed, not commanded)
    Write-Host "Remove: powershell -ExecutionPolicy Bypass -File `"$InstallDir\unin…ps1`""
    quoted
  • low Dangerous commands cmd-background-process install-watchdog.sh:302
    Starts a background / autostarted process
    nohup "${INSTALL_DIR}/gateway-watchdog.sh" >>"${STATE_DIR}/bootstrap.log" 2>&1 &
  • low Dangerous commands cmd-execpolicy-bypass README-watchdog.md:14
    Runs PowerShell with execution policy bypassed (documentation of a security skill)
    powershell -ExecutionPolicy Bypass -File .\inst…ps1
    security skill
  • low Dangerous commands cmd-execpolicy-bypass README.md:92
    Runs PowerShell with execution policy bypassed (documentation of a security skill)
    powershell -ExecutionPolicy Bypass -File .\inst…ps1
    security skill
  • low Dangerous commands cmd-execpolicy-bypass README.md:169
    Runs PowerShell with execution policy bypassed (documentation of a security skill)
    powershell -ExecutionPolicy Bypass -File "$env:LOCALAPPDATA\openclaw-gateway-watchdog\unin…ps1"
    security skill
  • low Dangerous commands cmd-execpolicy-bypass README.zh-CN.md:92
    Runs PowerShell with execution policy bypassed (documentation of a security skill)
    powershell -ExecutionPolicy Bypass -File .\inst…ps1
    security skill
  • low Dangerous commands cmd-execpolicy-bypass README.zh-CN.md:169
    Runs PowerShell with execution policy bypassed (documentation of a security skill)
    powershell -ExecutionPolicy Bypass -File "$env:LOCALAPPDATA\openclaw-gateway-watchdog\unin…ps1"
    security skill
  • low Dangerous commands cmd-execpolicy-bypass SKILL.md:59
    Runs PowerShell with execution policy bypassed (documentation of a security skill)
    powershell -ExecutionPolicy Bypass -File .\inst…ps1
    security skill

A further 2 matches are quotations in this security skill's documentation and are not counted as findings.

Files scanned: 18. 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 "requirements"
  • note frontmatter-key unknown frontmatter key "permissions"

Process rating: all ten parameters 63/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 2 mutating operations with no state check
  • 100Tools and files. No external tools needed
  • 100Steps. 6 steps
  • 100Failures and branches. 1 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 781 tokens
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing

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
  • +1No license
  • +2Single-language instructions
  • +3Description length 457: enough signal without eating the budget
  • +4Structure: 4 headings
  • +3Step-by-step instructions: 6 items
  • +4Has examples (7 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 68.

External checks

ClawHub: suspicious
This is a real OpenClaw watchdog, but it installs a persistent local control service with broad command execution paths and weak dashboard token handling that users should review before installing.
LLM: suspicious (high) · 28 May 2026