BB x402-wach
DeFi risk analysis toolkit powered by WACH.AI via x402 payments using AWAL wallet custody. Use when the user asks to check if a token is safe, assess DeFi risk, detect honeypots, analyze liquidity, holder distribution, or smart contract vulnerabilities for tokens on Ethereum, Polygon, Base, BSC, or Solana. Costs 0.01 USDC per query on Base.
As a process B 69/100 · Nearly there — weak spots: inputs and preconditions, consistency, 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 · 3
✓ No critical or high findings
Medium and low: 3
-
medium Risky intent
intent-wallet-secretsskill-card.md:29Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer targetRisk: Private key, seed phrase, or local wallet file handling could expose signing material.
-
medium Risky intent
intent-wallet-secretsSKILL.md:194Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target- Do not ask user for private key or seed phrase.
-
low Secrets in code
secret-high-entropy-tokenSKILL.md:165High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)const token = "0xA0…B48";
quoted
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 69/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 1 mutating operations with no state check
- 40Consistency. Frontmatter name (x402-wach) differs from the folder (wachai-x402)
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 100Steps. 53 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 3 branches, has a failure section
- 100Execution cost. Instruction body is 1394 tokens
- 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)
- +2Single-language instructions
- +3Description length 342: enough signal without eating the budget
- +4Structure: 15 headings
- +3Step-by-step instructions: 53 items
- +3Output format is stated explicitly
- +4Has examples (8 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.