SKILLEMALL.ai
RU Sign in

BC cdp-wallet

Send USDC on Base, read balances, and pay x402-protected resources using a Coinbase CDP server wallet (v2). Use when the operator needs the agent to make USDC payments, donations, or x402 settlements on Base without managing private keys directly. Wraps the official @coinbase/cdp-sdk into five CLI subcommands — address, balance, send-usdc, history, pay-x402 — that an agent can invoke directly. Wallet keys live in Coinbase's TEE infrastructure and are addressed by name, so the same wallet persists across container restarts. The pay-x402 subcommand handles the full x402 protocol negotiation (HTTP 402 → EIP-712-signed authorization → resubmit) using the same wallet.

ClawHub Agent Skills author: Ales375 v0.2.2 MIT-0 4 files body ≈ 3 042 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

As a process C 54/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

IntegrationAI and agentsInfrastructuretype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
B
89/100
safety, quality, tests
Safety 60%
92
Quality 40%
85
Run on models
none yet
Process rating
C
54/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Risky intent medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The purpose itself is risky: wallets, browser password stores, offensive security. Even an honest implementation gives the agent access to things that cost money.

For the author

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

    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 · 4

    ✓ No critical or high findings

    Medium and low: 4
    • medium Risky intent intent-wallet-secrets SKILL.md:49
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
      The wallet is a CDP server wallet — keys are generated and held inside AWS Nitro Enclaves on Coinbase's infrastructure, never on the operator's machine, and signing happens by API call against those h
    • low Risky intent intent-wallet-secrets SKILL.md:296
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)
      CDP server wallets v2 was chosen because: keys never reach the operator's filesystem (eliminates a whole class of leak); wallet creation is programmatic and idempotent (no interactive OTP, no seed phr
      quoted
    • low Secrets in code secret-high-entropy-token src/index.js:56
      High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
      usdc: "0x83…913",
      detector
    • low Secrets in code secret-high-entropy-token src/index.js:62
      High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
      usdc: "0x03…F7e",
      detector

    Files scanned: 4. 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 54/100

    • 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
    • 60Tools and files. Uses tools (web) that frontmatter does not declare
    • 85Steps. 31 steps, 2 vague phrases
    • 100Failures and branches. 6 branches, has a failure section
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 3042 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
    • +2Single-language instructions
    • +3Description length 671: enough signal without eating the budget
    • +4Structure: 18 headings
    • +3Step-by-step instructions: 31 items
    • +4Has examples (16 code blocks)
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.

    External checks

    ClawHub: suspicious
    This is an openly documented crypto wallet skill, but it lets an agent move funds and make paid web requests without built-in spending, recipient, domain, or network limits.
    LLM: suspicious (high) · VirusTotal: · 29 May 2026