BC einstein
Blockchain analytics and DeFi intelligence via Einstein's x402 micropayment services. Use when user wants on-chain market analysis, token research, whale tracking, smart money tracking, rug pull scanning, launchpad monitoring (Pump.fun, Zora, Virtuals), portfolio analysis, MEV detection, cross-chain arbitrage, or Polymarket data. Supports Base, Ethereum, BSC, Arbitrum, Polygon, Optimism, zkSync, Solana. Costs $0.25-$1.15 USDC per query via x402 protocol on Base.
As a process C 52/100 · 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 · 7
✓ No critical or high findings
Medium and low: 7
-
medium Risky intent
intent-wallet-secretsSKILL.md:48Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target- A **dedicated** wallet private key with USDC on Base network (do NOT use your main wallet)
-
low Secrets in code
secret-high-entropy-tokenreferences/examples.md:144High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file)node scripts/einstein.mjs wallet --chain ethereum --wallet 0xd8…045
fixture -
low Secrets in code
secret-high-entropy-tokenreferences/payment-guide.md:51High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)"verifyingContract": "0x83…913",
quoted -
low Secrets in code
secret-high-entropy-tokenreferences/payment-guide.md:70High-entropy token-like string (may be an id, hash or a credential)verifyingContract: 0x83…913
-
low Secrets in code
secret-high-entropy-tokenreferences/payment-guide.md:139High-entropy token-like string (may be an id, hash or a credential)cast call 0x83…913 \
-
low Secrets in code
secret-high-entropy-tokenreferences/payment-guide.md:190High-entropy token-like string (may be an id, hash or a credential) (documentation table row)| Token Address | `0x83…913` |
table -
low Secrets in code
secret-high-entropy-tokenscripts/einstein-setup.mjs:27High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)const USDC_BASE_ADDRESS = '0x83…913';
quoted
Files scanned: 10. 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 52/100
- 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
- 30Running it twice. 2 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, node) that frontmatter does not declare
- 100Steps. 13 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2285 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low The response is described with custom markup (3 tags): a typed call is more reliable
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
- -31 of 3 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 466: enough signal without eating the budget
- +4Structure: 20 headings
- +3Step-by-step instructions: 13 items
- +4Has examples (10 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.