BC paytoll
27 tools for DeFi, DEX swaps, cross-chain bridges, Twitter/X, on-chain token data, crypto utilities, and LLM access via x402 micro-payments on Base. No API keys needed — payment is the auth.
As a process C 59/100 · 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 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
- 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 · 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 MCP package receives a raw wallet private key and is installed from npm without a pinned version in this artifact.
-
medium Risky intent
intent-wallet-secretsSKILL.md:18Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target- A **dedicated** wallet private key set as `PRIVATE_KEY` in their environment (do not reuse your main wallet — use a wallet with minimal funds)
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - note
frontmatter-keyunknown frontmatter key "requires.env" - note
frontmatter-keyunknown frontmatter key "requires.bins" - note
frontmatter-keyunknown frontmatter key "homepage" - note
frontmatter-keyunknown frontmatter key "repository"
Process rating: all ten parameters 59/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 55Failures and branches. 1 branches
- 100Tools and files. No external tools needed
- 100Steps. 61 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2570 tokens
- 100Running it twice. Mutating operations check current state
- 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
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +3Description length 190: enough signal without eating the budget
- +4Structure: 13 headings
- +3Step-by-step instructions: 61 items
Quality base 70; lint remarks subtract, signals add up to 100. Result: 65.