SKILLEMALL.ai
GitHub ↗ RU Sign in

CF gateway-watchdog

Monitor the OpenClaw Gateway plus configured Spark, Local API Hub, and Dashboard loopback health endpoints with a read-only watchdog state machine, local state files, cooldown dedupe, and optional Discord alerts on macOS. Use for explicitly configured foreground checks, cron execution, LaunchAgent installation, recovery notification, and low-noise incident reporting; it does not rewrite OpenClaw config or restart services.

Not recommendedcritical or high security findings
ClawHub Agent Skills author: Jonathan Jing v1.0.4 MIT-0 9 files · 3 scripts body ≈ 979 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process F 40/100 · Will not run — References files that are not bundled: references/com.openclaw.gateway-watchdog.plist.template

IntegrationDiscordInfrastructureData and analyticstype 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
73/100
safety, quality, tests
Safety 60%
70
Quality 40%
77
Run on models
none yet
Process rating
F
40/100
Will not run
References files that are not bundled: references/com.openclaw.gateway-watchdog.plist.template
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.

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. 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

  • high Dangerous commands cmd-persistence scripts/install-launchd.sh:69
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    launchctl bootstrap "gui/$UID" "$LAUNCHD_PLIST"
Medium and low: 4
  • medium Exfiltration net-credential-use scripts/gateway-watchdog.sh:210
    Credential used in a network call (verify the destination is the intended service)
    curl_args+=(-H "Authorization: Bearer ${spark_token}")
  • medium Dangerous commands cmd-persistence scripts/install-launchd.sh:74
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
    echo "  launchctl bootstrap gui/$UID \"$LAUNCHD_PLIST\""
    code literal
  • low Exfiltration exfil-webhook-url README.md:116
    Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
    export DISCORD_WEBHOOK_URL="https://discord.com/api/webhooks/..."
    placeholder
  • low Exfiltration exfil-webhook-url SKILL.md:104
    Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
    export DISCORD_WEBHOOK_URL="https://discord.com/api/webhooks/..."
    placeholder

Files scanned: 9. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning missing-ref reference to a missing file: references/com.openclaw.gateway-watchdog.plist.template

Process rating: all ten parameters 40/100

Will not run. References files that are not bundled: references/com.openclaw.gateway-watchdog.plist.template
  • 0Tools and files. 1 referenced file(s) missing: references/com.openclaw.gateway-watchdog.plist.template
  • 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
  • 40Consistency. Frontmatter name (gateway-watchdog) differs from the folder (openclaw-gateway-watchdog-skill)
  • 100Steps. 25 steps
  • 100Failures and branches. 1 branches, has a failure section
  • 100Execution cost. Instruction body is 979 tokens
  • 100Progress reporting. Reports progress

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
  • -31 of 3 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +3Description length 426: enough signal without eating the budget
  • +4Structure: 11 headings
  • +3Step-by-step instructions: 25 items
  • +4Has examples (7 code blocks)
  • +4Reference files are cited in the instructions (1 of 1)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 77.

External checks

ClawHub: suspicious
The watchdog mostly matches its stated monitoring purpose, but it can repeatedly send a Spark API token to any configured Spark URL, so it needs user review before installation.
LLM: suspicious (high) · VirusTotal: · 3 Aug 2026