DF hour-meter
Track elapsed time from a set epoch with tamper-evident locking. Like an analog Hobbs meter but digital. Use for tracking uptime, service hours, time since events, sobriety counters, project duration, equipment runtime. Supports create, lock (seal), check, verify against external hash, list, and export operations.
Track elapsed time from a set epoch with tamper-evident locking.
As a process F 28/100 · Will not run — References files that are not bundled: docs/sendgrid-webhook-setup.png
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 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".
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
- 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.
- The text references files that are not there: add them or drop the references.
- 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 · 8
-
high Exfiltration
exfil-webhook-urlREADME.md:199Webhook / callback URL commonly used for exfiltration (verify the destination)--discord-webhook https://discord.com/api/webhooks/xxx/yyy
-
high Exfiltration
exfil-webhook-urlREADME.md:243Webhook / callback URL commonly used for exfiltration (verify the destination)# Gives you: https://random-words.trycloudflare.com
-
high Exfiltration
exfil-webhook-urlSKILL.md:183Webhook / callback URL commonly used for exfiltration (verify the destination)python sendgrid_webhook.py --port 8089 --discord-webhook https://discord.com/api/webhooks/xxx/yyy
Medium and low: 5
-
medium Exfiltration
exfil-webhook-urlscripts/check-webhook-services.sh:27Webhook / callback URL commonly used for exfiltration (verify the destination) (detector / deny-list definition)TUNNEL_URL=$(grep -o 'https://[^[:space:]]*trycloudflare.com' /tmp/cloudflared.log | head -1)
detector -
medium Exfiltration
exfil-webhook-urlscripts/check-webhook-services.sh:38Webhook / callback URL commonly used for exfiltration (verify the destination) (detector / deny-list definition)TUNNEL_URL=$(grep -o 'https://[^[:space:]]*trycloudflare.com' /tmp/cloudflared.log 2>/dev/null | head -1)
detector -
medium Exfiltration
exfil-webhook-urlscripts/sendgrid_webhook.py:500Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)python sendgrid_webhook.py --port 8089 --discord-webhook https://discord.com/api/webhooks/xxx/yyy
quoted -
low Exfiltration
exfil-webhook-urlREADME.md:262Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)--discord-webhook "https://discord.com/api/webhooks/YOUR_ID/YOUR_TOKEN"
placeholder -
low Exfiltration
read-dotenvscripts/check-webhook-services.sh:5Reads a .env file (code comment)# Source .env for Discord webhook URL
comment
Files scanned: 7. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: docs/sendgrid-webhook-setup.png - note
frontmatter-keyunknown frontmatter key "clawhub"
Process rating: all ten parameters 28/100
- 0Tools and files. 1 referenced file(s) missing: docs/sendgrid-webhook-setup.png
- 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
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 20 mutating operations with no state check
- 40Consistency. Frontmatter name (hour-meter) differs from the folder (tardis)
- 85Steps. 38 steps, 1 vague phrases
- 100Execution cost. Instruction body is 2121 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
- -31 of 3 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 315: enough signal without eating the budget
- +4Structure: 20 headings
- +3Step-by-step instructions: 38 items
- +4Has examples (14 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.