AC use-maskrun
Use maskrun instead of executing shell commands directly when commands may print environment variables, API keys, tokens, passwords, secrets, credentials, CI variables, cloud credentials, .env values, or other sensitive values. Trigger this skill before running terminal commands, test commands, build scripts, curl/API calls, package manager scripts, debugging commands, or agent automation where stdout or stderr might contain secret environment variable values.
As a process C 50/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- 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 · 2
✓ No critical or high findings
Medium and low: 2
-
low Exfiltration
exfil-secret-in-urlSKILL.md:23Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (placeholder value)maskrun -- curl "https://api.example.com?key=…"
placeholder -
low Exfiltration
net-credential-useSKILL.md:23Credential used in a network call (verify the destination is the intended service) (security demo / example)maskrun -- curl "https://api.example.com?key=…"
demo
Files scanned: 5. 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 50/100
- 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
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 1 mutating operations with no state check
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 65Failures and branches. 3 branches
- 100Steps. 10 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 845 tokens
- 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)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 464: enough signal without eating the budget
- +4Structure: 8 headings
- +3Step-by-step instructions: 10 items
- +4Has examples (8 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.