SKILLEMALL.ai

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.

ClawHub Agent Skills author: CartonPliant v1.3.6 MIT-0 3 files body ≈ 1 759 tokens Open the sourceclawhub.ai analyzed 2 d ago

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

IntegrationInfrastructuretype and topics are labelled automatically from the skill text
JSON
Technical rating
B
78/100
safety, quality, tests
Safety 60%
90
Quality 40%
61
Run on models
none yet
Process rating
B
66/100
Nearly there
Result and completion w 14
0
Inputs and preconditions w 11
0
Running it twice w 4
30
the three weakest of ten parameters · all ten

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
For the model run — optional
  • 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-token SKILL.md:16
    High-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-token SKILL.md:40
    High-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-token SKILL.md:41
    High-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-token SKILL.md:72
    High-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-token SKILL.md:82
    High-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-token verify-approve.mjs:5
    High-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-token verify-approve.mjs:6
    High-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-token verify-approve.mjs:7
    High-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-token verify-approve.mjs:8
    High-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-token verify-approve.mjs:9
    High-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-yaml SKILL.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-when description does not say WHEN to use the skill (no "use when")
  • note frontmatter-key unknown 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.

External checks

ClawHub: clean
The skill is a disclosed Base blockchain analysis helper that requires fresh user approval before paid calls or transaction-related actions, with only a minor broad-trigger caveat.
LLM: benign (high) · VirusTotal: · 8 Sept 2026