BC clawxpay
Pay-per-call API gateway — zero account, zero API key, zero subscription via the x402 protocol. One Base wallet + USDC is all you need to access 250+ professional API endpoints on a per-call basis: real-time crypto prices and on-chain data (coinank · nofxos · coinmarketcap), US stock options and technical indicators (alphavantage · polygon · alpaca · twelvedata), China A-share market (tushare), Web3 project funding intelligence (rootdata), and 7 AI model providers (OpenAI · Anthropic · DeepSeek · Qwen · Gemini · Grok · Kimi). From $0.001 per call — settled on-chain instantly — native payment capability for Agents.
As a process C 63/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
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 purpose itself is risky: wallets, browser password stores, offensive security. Even an honest implementation gives the agent access to things that cost money.
Explain in the description why the access is needed and how it is limited; add tests that show refusals on dangerous requests.
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 Risky intent
intent-wallet-secretsskill-card.md:24Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer targetRisk: The local wallet private key is sensitive and stored on disk. <br>
-
medium Risky intent
intent-wallet-secretsskill.md:17Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer targetdescription: Wallet private key — written on first install, permissions 0600 (owner read/write only), never transmitted to any server
Files scanned: 2. 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 63/100
- 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. 3 mutating operations with no state check
- 60Tools and files. Uses tools (bash, web, python, node) that frontmatter does not declare
- 70Execution cost. Instruction body is 4125 tokens
- 100Steps. 57 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- 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 621: enough signal without eating the budget
- +4Structure: 26 headings
- +3Step-by-step instructions: 57 items
- +4Has examples (8 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.