BF dyagil-services-watchdog
Set up a systemd-based watchdog that keeps long-running Node.js services (Telegram bots, Express dashboards, etc.) alive across shell exits, ssh disconnects, agent-runtime restarts, and server reboots. Use whenever the user reports "the bot died again", "service is down after restart", or after any event that may have killed child processes. Provides a 2-minute user-systemd timer that detects and auto-restarts services with their `.env` correctly loaded.
As a process F 42/100 · Will not run — References files that are not bundled: scripts/sahi-watchdog.service, scripts/sahi-watchdog.timer
AnalyzerTelegramData and analyticsAI and agentsInfrastructuretype and topics are labelled automatically from the skill text
How to improve
- 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 · 11
✓ No critical or high findings
Medium and low: 11
-
low Exfiltration
exfil-webhook-urlscripts/services-watchdog.sh:35Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)curl -s --max-time 10 -X POST "https://api.telegram.org/bot${token}/sendMessage" \placeholder -
low Exfiltration
net-credential-usescripts/services-watchdog.sh:35Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host)curl -s --max-time 10 -X POST "https://api.telegram.org/bot${token}/sendMessage" \vendor-host -
low Dangerous commands
cmd-background-processscripts/services-watchdog.sh:50Starts a background / autostarted process (quoted — discussed, not commanded)bash -c 'cd '"$WORKSPACE"'/projects/sahi-diet && set -a && [ -f .env ] && . ./.env; set +a; exec nohup node src/bot.js >> logs/bot.log 2>&1 < /dev/null' &
quoted -
low Dangerous commands
cmd-background-processscripts/services-watchdog.sh:51Starts a background / autostarted processdisown 2>/dev/null || true
-
low Dangerous commands
cmd-background-processscripts/services-watchdog.sh:64Starts a background / autostarted process (quoted — discussed, not commanded)bash -c 'cd '"$WORKSPACE"'/projects/sahi-mind && set -a && [ -f .env ] && . ./.env; set +a; exec nohup node src/index.js >> logs/mind.log 2>&1 < /dev/null' &
quoted -
low Dangerous commands
cmd-background-processscripts/services-watchdog.sh:65Starts a background / autostarted processdisown 2>/dev/null || true
-
low Dangerous commands
cmd-background-processscripts/services-watchdog.sh:83Starts a background / autostarted process (quoted — discussed, not commanded)bash -c 'cd '"$WORKSPACE"'/projects/mission-control && set -a && [ -f .env ] && . ./.env; set +a; exec nohup node server.js >> logs/mc.log 2>&1 < /dev/null' &
quoted -
low Dangerous commands
cmd-background-processskill-card.md:25Starts a background / autostarted processMitigation: Create and review the user service and timer unit files yourself before running systemctl enable or start commands. <br>
-
low Dangerous commands
cmd-background-processSKILL.md:13Starts a background / autostarted process (quoted — discussed, not commanded)Long-running Node services launched from a parent shell (or as children of an agent runtime) die when the parent exits. Runtime restarts are especially aggressive — they tend to take down everything t
quoted -
low Dangerous commands
cmd-background-processSKILL.md:91Starts a background / autostarted process (quoted — discussed, not commanded)bash -c 'cd '"$WORKSPACE"'/projects/myservice && set -a && [ -f .env ] && . ./.env; set +a && exec nohup node src/index.js >> logs/svc.log 2>&1 < /dev/null' &
quoted -
low Dangerous commands
cmd-background-processSKILL.md:92Starts a background / autostarted processdisown 2>/dev/null || true
Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: scripts/sahi-watchdog.service - warning
missing-refreference to a missing file: scripts/sahi-watchdog.timer
Process rating: all ten parameters 42/100
Will not run. References files that are not bundled: scripts/sahi-watchdog.service, scripts/sahi-watchdog.timer
- 0Tools and files. 2 referenced file(s) missing: scripts/sahi-watchdog.service, scripts/sahi-watchdog.timer
- 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
- 30Running it twice. 1 mutating operations with no state check
- 100Steps. 10 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1139 tokens
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
- +2Single-language instructions
- +5Description quotes 2 example trigger phrases
- +3Description length 458: enough signal without eating the budget
- +4Structure: 9 headings
- +3Step-by-step instructions: 10 items
- +4Has examples (5 code blocks)
- +3All 1 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.
External checks
ClawHub: suspicious
The skill is mostly a legitimate watchdog helper, but its included script is personalized and can use a local Telegram bot token to send status messages to a hard-coded chat without clear user control.
LLM: suspicious (high) · VirusTotal: · 29 May 2026