DC pve-builder
Proxmox VE VM builder with cloud-init automation, config-driven hardware defaults, validation, and static IP support
As a process C 64/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
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.
- 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 · 7
-
high Dangerous commands
cmd-destructive-fs-scopedqm-reference.md:118Destructive command on a partition / current directory (normal in admin docs; verify the target)- mkfs.ext4 /dev/sdb
-
high Dangerous commands
cmd-destructive-fs-scopedqm-reference.md:119Destructive command on a partition / current directory (normal in admin docs; verify the target)- mkfs.ext4 /dev/sdc
-
high Dangerous commands
cmd-destructive-fs-scopedqm-reference.md:192Destructive command on a partition / current directory (normal in admin docs; verify the target)- mkfs.ext4 /dev/sdb # First data disk (scsi)
-
high Dangerous commands
cmd-destructive-fs-scopedqm-reference.md:197Destructive command on a partition / current directory (normal in admin docs; verify the target)- mkfs.ext4 /dev/sdc # Second data disk (scsi)
Medium and low: 3
-
low Secrets in code
secret-private-keyagent.js:189Private key material (placeholder value)await writeFile(priv, `-----BEGIN PRIVATE KEY----- …`);
placeholder -
low Dangerous commands
cmd-background-processagent.js:425Starts a background / autostarted process (string literal in code, not executed)userData += `\nruncmd:\n - systemctl enable qemu-guest-agent\n - systemctl start qemu-guest-agent\n - echo "Cloud-init complete at $(date)" >> /var/log/cloud-init-complete.log\n`;
code literal -
low Dangerous commands
cmd-background-processqm-reference.md:186Starts a background / autostarted process- systemctl enable qemu-guest-agent
Files scanned: 5. 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") - note
frontmatter-keyunknown frontmatter key "permissions" - note
frontmatter-keyunknown frontmatter key "tools"
Process rating: all ten parameters 64/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 8 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 95 steps
- 100Failures and branches. 8 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3184 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 11 top-level sections: this looks like several domains in one skill
- high The skill tells the model to perform an irreversible action with no human approval
- low The response is described with custom markup (6 tags): a typed call is more reliable
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 116: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 21 headings
- +3Step-by-step instructions: 95 items
- +4Has examples (3 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 67.