DC gateway-watchdog
Self-healing watchdog for OpenClaw gateway. Auto-backup openclaw.json before changes, health-check the gateway process, and auto-rollback to last known good config on failure. Use when setting up gateway resilience, self-recovery, auto-restart, config backup, or when the user mentions watchdog, self-heal, gateway down, or config recovery.
As a process C 57/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency
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.
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.
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
- 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.
- 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 · 12
-
high Dangerous commands
cmd-persistencereferences/launchd.md:31Persistence mechanism (cron / launchd / scheduled task / autorun registry)sed -i '' "s/USERNAME/$(whoami)/g" ~/Library/LaunchAgents/ai.openclaw.watchdog.plist
-
high Dangerous commands
cmd-persistencereferences/launchd.md:33Persistence mechanism (cron / launchd / scheduled task / autorun registry)launchctl load ~/Library/LaunchAgents/ai.openclaw.watchdog.plist
-
high Dangerous commands
cmd-persistencescripts/setup-watchdog.sh:122Persistence mechanism (cron / launchd / scheduled task / autorun registry)(crontab -l 2>/dev/null | grep -v "watchdog.sh") | crontab -
-
high Dangerous commands
cmd-persistencescripts/setup-watchdog.sh:125Persistence mechanism (cron / launchd / scheduled task / autorun registry)(crontab -l 2>/dev/null; echo "$CRON_JOB") | crontab -
Medium and low: 8
-
medium Dangerous commands
cmd-persistencereferences/launchd.md:27Persistence mechanism (cron / launchd / scheduled task / autorun registry) (quoted — discussed, not commanded)Save as `~/Library/LaunchAgents/ai.openclaw.watchdog.plist`, then:
quoted -
medium Dangerous commands
cmd-persistenceSKILL.md:44Persistence mechanism (cron / launchd / scheduled task / autorun registry) (detector / deny-list definition)crontab -l | grep -v watchdog | crontab -
detector -
low Dangerous commands
cmd-background-processreferences/systemd.md:30Starts a background / autostarted processsudo systemctl enable openclaw-watchdog.timer
-
low Dangerous commands
cmd-cron-mentionscripts/setup-watchdog.sh:122Mentions editing / listing crontab(crontab -l 2>/dev/null | grep -v "watchdog.sh") | crontab -
-
low Dangerous commands
cmd-cron-mentionscripts/setup-watchdog.sh:125Mentions editing / listing crontab(crontab -l 2>/dev/null; echo "$CRON_JOB") | crontab -
-
low Dangerous commands
cmd-cron-mentionscripts/setup-watchdog.sh:137Mentions editing / listing crontab (detector / deny-list definition; string literal in code, not executed)echo " 제거: crontab -l | grep -v watchdog | crontab -"
detectorcode literal -
low Dangerous commands
cmd-cron-mentionscripts/watchdog-status.sh:13Mentions editing / listing crontabif crontab -l 2>/dev/null | grep -q "watchdog.sh"; then
-
low Dangerous commands
cmd-cron-mentionSKILL.md:44Mentions editing / listing crontabcrontab -l | grep -v watchdog | crontab -
Files scanned: 7. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 57/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 2 mutating operations with no state check
- 40Consistency. Frontmatter name (gateway-watchdog) differs from the folder (gw-self-heal)
- 50Failures and branches. 0 branches, has a failure section
- 70When it triggers. States when to use, but not when not to
- 85Steps. 12 steps, 1 vague phrases
- 100Tools and files. No external tools needed
- 100Execution cost. Instruction body is 468 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
- +1No license
- +2Single-language instructions
- +3Description length 340: enough signal without eating the budget
- +4Structure: 8 headings
- +3Step-by-step instructions: 12 items
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
- +3All 2 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.