BC privileged-operations
Safely perform Linux tasks that may require root privileges. Keep work unprivileged by default. When root is genuinely required, make the exact privileged action and reason visible to the user, then elevate only that narrow operation through an interactive authentication path the user can see and control. Prefer pkexec on graphical desktops; use sudo or doas only when their prompt is genuinely visible to the user. Never ask for, capture, pipe, cache, or automate a user's password, and never silently fall back to hidden or broad root execution.
Safely perform Linux tasks that may require root privileges.
As a process C 55/100 · Has gaps — weak spots: result and completion, inputs and preconditions
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 · 3
-
high Dangerous commands
cmd-pipe-to-shellSKILL.md:365Downloads and executes remote code from an unrecognised host (pipe to shell)curl ... | sudo sh
Medium and low: 2
-
medium Dangerous commands
cmd-privilegeSKILL.md:365Privilege escalation / world-writable permissionscurl ... | sudo sh
-
low Dangerous commands
cmd-privilegeSKILL.md:436Privilege escalation / world-writable permissions (negated — the text forbids it)- set unsafe setuid bits;
negated
Files scanned: 2. 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 55/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 50When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, node) that frontmatter does not declare
- 85Steps. 91 steps, 1 vague phrases
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3649 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 17 top-level sections: this looks like several domains in one skill
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 549: enough signal without eating the budget
- +4Structure: 21 headings
- +3Step-by-step instructions: 91 items
- +4Has examples (22 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.