AC safe-fuzzer
Sandbox-only behavior-led gray-box skill fuzzer. Spawns a worker subagent, probes an installed target skill, deploys honeypot fixtures, and returns a structured JSON risk report.
As a process C 62/100 · Has gaps — weak spots: when it triggers, consistency, running it twice
How to improve
- 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 · 1
✓ No critical or high findings
Medium and low: 1
✓ Guard found no suspicious behaviour. 1 matches are attack strings quoted in this security skill's own documentation.
Files scanned: 7. 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")
Process rating: all ten parameters 62/100
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 14 mutating operations with no state check
- 40Consistency. Frontmatter name (safe-fuzzer) differs from the folder (safe-fuzzer-deprecated)
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Failures and branches. 8 branches
- 100Steps. 120 steps
- 100Execution cost. Instruction body is 3412 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 10 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)
- +1No license
- +2Single-language instructions
- +3Description length 178: enough signal without eating the budget
- +4Structure: 20 headings
- +3Step-by-step instructions: 120 items
- +3Output format is stated explicitly
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.