CF unraid-claw
Query an Unraid server via GraphQL for system, array, and Docker status in read-only mode.
As a process F 59/100 · Will not run — References files that are not bundled: scripts/unraid_monitor.cron.template
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.
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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 · 4
-
high Dangerous commands
cmd-persistenceREADME.md:152Persistence mechanism (cron / launchd / scheduled task / autorun registry)cat /tmp/current.cron scripts/unraid_monitor.cron.template | crontab -
Medium and low: 3
-
low Dangerous commands
cmd-privilegeREADME.md:51Privilege escalation / world-writable permissions (quoted — discussed, not commanded)`sudo cp unraid-selfsigned.crt /usr/local/share/ca-certificates/unraid-selfsigned.crt`
quoted -
low Exfiltration
read-dotenvREADME.md:73Reads a .env filesource .env
-
low Dangerous commands
cmd-cron-mentionREADME.md:151Mentions editing / listing crontabcrontab -l > /tmp/current.cron 2>/dev/null || true
Files scanned: 13. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
missing-refreference to a missing file: scripts/unraid_monitor.cron.template
Process rating: all ten parameters 59/100
- 0Tools and files. 1 referenced file(s) missing: scripts/unraid_monitor.cron.template
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 1 mutating operations with no state check
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 100Steps. 91 steps
- 100Failures and branches. 11 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1880 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)
- +3Description length 90: 120–800 characters recommended
- -31 of 10 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +4Structure: 14 headings
- +3Step-by-step instructions: 91 items
- +3Output format is stated explicitly
- +4Has examples (4 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 63.