AC cardzero
CardZero — the first payment wallet built for AI agents. Create USDC wallets on Base L2, make payments, pay x402 paywalls, pay other agents, check balance, view transactions, and run A2A jobs with on-chain escrow (ERC-8183). Human owner sets spending rules via Dashboard; agent pays autonomously within limits. Use when agent needs to: 'pay for API access', 'send USDC', 'pay 402 paywall', 'create a wallet', 'check my balance', 'make a payment', 'buy with crypto', 'agent wallet', 'autonomous payment', 'micropayment', 'pay another agent', 'agent-to-agent payment', 'A2A payment', 'hire another agent', 'job escrow', 'pay on delivery'.
As a process C 53/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The files contain someone else's key or token. If it is live, your agent will call third-party services under a stranger's identity; if it was revoked, the skill's scripts simply fail. Such a key often arrives with the author's whole workspace, personal data included.
The key is visible to everyone who downloaded the skill and has likely been copied by catalog-scanning bots already. Revoke it now, check bills and access logs, then reissue.
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
-
medium Secrets in code
secret-labelled-tokenSKILL.md:66Labelled token / key literal (vendor format unknown — verify it is not a live credential)API Key: czap…3x4
-
low Secrets in code
secret-high-entropy-tokenSKILL.md:250High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)"asset": "0x83…913"
quoted
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "requires"
Process rating: all ten parameters 53/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 13 mutating operations with no state check
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 85Steps. 56 steps, 1 vague phrases
- 100Failures and branches. 4 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3134 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
- +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 636: enough signal without eating the budget
- +4Structure: 24 headings
- +3Step-by-step instructions: 56 items
- +4Has examples (20 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.