AC ai-agent-governance
Register an autonomous agent's identity, check a runtime policy decision before it acts, and log a hash-chained attestation of what it did. Backed by A2Z SOC's live Agent Registry, Policy Firewall, and Attestation Ledger.
Register an autonomous agent's identity, check a runtime policy decision before it acts, and log a hash-chained attestation of what it did.
As a process C 57/100 · Has gaps — weak spots: result and completion, 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 · 2
✓ No critical or high findings
Medium and low: 2
-
low Exfiltration
intent-browser-credential-storeSKILL.md:80Accesses a browser credential / cookie store (negated — the text forbids it)An agent that can act without an independent identity, a policy check outside its own reasoning, and a tamper-evident log of what it did is a liability the moment it's trusted with anything real, spen
negated
A further 1 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 57/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 1 mutating operations with no state check
- 55Failures and branches. 1 branches
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 75Steps. 3 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 946 tokens
- 100Progress reporting. Reports progress
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
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 221: enough signal without eating the budget
- +4Structure: 6 headings
- +3Step-by-step instructions: 3 items
- +4Has examples (3 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.