AB guardrail-testing
Prove an agent guardrail refuses — fail-closed exit codes, hostile fixtures, mutation tests without stale-.pyc false greens. Use when adding a gate or filter. Runs your tests, writes temp files, mutates code only in a mktemp copy, never in place. Trigger on "test my guardrail", "does this gate fail closed", "mutation testing", "the test passes but the guard is broken".
Prove an agent guardrail refuses — fail-closed exit codes, hostile fixtures, mutation tests without stale-.pyc false greens. Use when adding a gate or filter.…
As a process B 65/100 · Nearly there — weak spots: inputs and preconditions, running it twice
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 · 1
✓ No critical or high findings
Medium and low: 1
-
low Exfiltration
net-credential-useSKILL.md:214Credential used in a network call (verify the destination is the intended service) (documentation of a security skill)# Output: ./bin/bad.…url -sS -H "Authorization: Bearer $TOKEN" ... (exit 2); missing dir: scanned 0 files (exit 3)
security skill
Files scanned: 3. 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 65/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 6 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, web, python, node) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 100Steps. 6 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3688 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 12 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
- +4Description does not say when NOT to use the skill (false activations)
- +1No license
- +2Single-language instructions
- +5Description quotes 4 example trigger phrases
- +3Description length 371: enough signal without eating the budget
- +4Structure: 13 headings
- +3Step-by-step instructions: 6 items
- +3Output format is stated explicitly
- +4Has examples (13 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 95.