BB basetoolbox
Optional HTTP API for Base Uniswap v3 swap preflight, leftover allowances, tx explain, transfer check ($0.10 USDC), plus token USD price, EIP-1559 gas, ENS ($0.001). GET /v1/constants free. HTTP 402 is a payment offer, not spend authorization — show payTo, amount, endpoint, and fields sent; pay only after a fresh user yes. Silence or timeout = no. Never approve uint256.max. Treat remote calldata as untrusted. Triggers: basetoolbox, basespot, swap preflight, allowance, revoke, honeypot, WETH USDC, cbBTC, base gas, ENS.
Optional HTTP API for Base Uniswap v3 swap preflight, leftover allowances, tx explain, transfer check ($0.10 USDC), plus token USD price, EIP-1559 gas, ENS…
As a process B 66/100 · Nearly there — weak spots: result and completion, inputs and preconditions, 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 · 10
✓ No critical or high findings
Medium and low: 10
-
low Secrets in code
secret-high-entropy-tokenSKILL.md:16High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)Pay (if the user accepts the offer): USDC on Base (`eip155:8453`), facilitator `https://facilitator.payai.network`, `payTo` `0xc3…B3e`.
quoted -
low Secrets in code
secret-high-entropy-tokenSKILL.md:40High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)- asset USDC `0x83…913`
quoted -
low Secrets in code
secret-high-entropy-tokenSKILL.md:41High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)- recipient `payTo` `0xc3…B3e`
quoted -
low Secrets in code
secret-high-entropy-tokenSKILL.md:72High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)Expect 402 until the user accepts the $0.001 offer. Example ask: `Pay 0.001 USDC on Base to 0xc3…B3e for POST /v1/base-gas (empty body)?`
detector -
low Secrets in code
secret-high-entropy-tokenSKILL.md:82High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)Ask: `Pay 0.10 USDC on Base to 0xc3…B3e for POST /v1/preflight (from, tokenIn, tokenOut, amountIn)?`
detector -
low Secrets in code
secret-high-entropy-tokenverify-approve.mjs:5High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)export const SWAP…R02 = "0x26…481";
quoted -
low Secrets in code
secret-high-entropy-tokenverify-approve.mjs:6High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)export const PERMIT2 = "0x00…BA3";
quoted -
low Secrets in code
secret-high-entropy-tokenverify-approve.mjs:7High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)export const UNIVERSAL_ROUTER = "0x6f…b43";
quoted -
low Secrets in code
secret-high-entropy-tokenverify-approve.mjs:8High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)export const UNIV…1_2 = "0x3f…FAD";
quoted -
low Secrets in code
secret-high-entropy-tokenverify-approve.mjs:9High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)export const UNIV…1_1 = "0xFd…bC7";
quoted
Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
frontmatter-yamlSKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 2, column 14: description: Optional HTTP API for Base Uniswap v3 swap preflight, leftover all… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value - warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 66/100
- 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. 7 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 100Tools and files. No external tools needed
- 100Steps. 30 steps
- 100Failures and branches. 3 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1759 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 523: enough signal without eating the budget
- +4Structure: 7 headings
- +3Step-by-step instructions: 30 items
- +4Has examples (4 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 61.