SKILLEMALL.ai
RU Sign in

DC agent-wallet

Multi-chain wallet management for AI agents. Create wallets, check balances, transfer tokens (USDC/native), and bridge cross-chain. Use when agents need to send/receive payments, check funds, or manage crypto wallets. Supports Solana, Base, and Ethereum. Trigger phrases include "create wallet", "check balance", "send USDC", "transfer", "my addresses", "wallet status".

Not recommendedlow grade D
ClawHub Agent Skills author: voltagemonke v0.1.0 15 files body ≈ 1 132 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

As a process C 52/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, consistency

GeneratorAI and agentstype 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
D
57/100
safety, quality, tests
Safety 60%
33
Quality 40%
93
Run on models
none yet
Process rating
C
52/100
Has gaps
Inputs and preconditions w 11
0
Progress reporting w 2
0
When it triggers w 12
20
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 · 39

    ✓ No critical or high findings

    Medium and low: 39
    • medium Risky intent intent-wallet-secrets README.md:159
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
      # Edit .env with your seed phrase
    • medium Risky intent intent-wallet-secrets README.md:178
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
      Seed Phrase: [12 words - SAVE SECURELY!]
    • medium Risky intent intent-wallet-secrets README.md:311
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
      - HD wallet derived from BIP-39 seed phrase
    • medium Risky intent intent-wallet-secrets README.md:313
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
      - **Never share or commit your seed phrase**
    • medium Risky intent intent-wallet-secrets skill-card.md:22
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
      Risk: Seed phrase exposure or reuse can compromise all funds controlled by the wallet. <br>
    • medium Risky intent intent-wallet-secrets SKILL.md:8
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
      Multi-chain wallet skill for AI agents. One seed phrase, all chains.
    • medium Risky intent intent-wallet-secrets SKILL.md:29
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
      Generates BIP-39 seed phrase, derives addresses for all chains. Shows seed ONCE with security warning.
    • low Secrets in code secret-high-entropy-token data/bridge-states.json:9
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      "walletAddress": "0xbF…cC8",
      quoted
    • low Secrets in code secret-high-entropy-token data/bridge-states.json:17
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      "error": "execution reverted: \"ERC20: transfer amount exceeds allowance\" (action=\"estimateGas\", data=\"0x08…000
      quoted
    • low Secrets in code secret-high-entropy-token data/bridge-states.json:27
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      "walletAddress": "0xbF…cC8",
      quoted
    • low Secrets in code secret-high-entropy-token data/bridge-states.json:35
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      "error": "execution reverted (no data present; likely require(false) occurred (action=\"estimateGas\", data=\"0x\", reason=\"require(false)\", transaction={ \"data\": \"0x6f…000
      quoted
    • low Secrets in code secret-high-entropy-token data/bridge-states.json:45
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      "walletAddress": "0xbF…cC8",
      quoted
    • low Secrets in code secret-high-entropy-token package-lock.json:80
      High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
      "integrity": "sha5…jyV+xktW…ZFZ+Q==",
      detector
    • low Secrets in code secret-high-entropy-token package-lock.json:151
      High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
      "integrity": "sha5…m48+9Ovm…EqH/ti/7ASj…sop+LQ==",
      detector
    • low Secrets in code secret-high-entropy-token package-lock.json:169
      High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
      "integrity": "sha5…kJw+JUEz…Ry8+JzNy…KLw==",
      detector
    • low Secrets in code secret-high-entropy-token package-lock.json:206
      High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
      "integrity": "sha512-GhH/abcC…hoN+uBNo…mU1+t8xT…EBA==",
      detector
    • low Secrets in code secret-high-entropy-token package-lock.json:250
      High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
      "integrity": "sha5…Z4v+DkGoC42/TS2ond+PARCxTJvgTFUNDZovyQ/uAQ4…g7A==",
      detector
    • low Exfiltration read-dotenv README.md:158
      Reads a .env file
      cp .env.example .env
    • low Secrets in code secret-high-entropy-token references/chains.md:17
      High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
      | Solana | `EPjF…t1v` | 6 |
      table
    • low Secrets in code secret-high-entropy-token references/chains.md:18
      High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
      | Base | `0x83…913` | 6 |
      table
    • low Secrets in code secret-high-entropy-token references/chains.md:19
      High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
      | Ethereum | `0xA0…B48` | 6 |
      table
    • low Secrets in code secret-high-entropy-token references/chains.md:25
      High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
      | Solana | Devnet | `4zMM…cDU` | 6 |
      table
    • low Secrets in code secret-high-entropy-token references/chains.md:26
      High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
      | Base | Sepolia | `0x03…F7e` | 6 |
      table
    • low Secrets in code secret-high-entropy-token scripts/bridge-async.js:37
      High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
      usdc: '0x03…F7e',
      detector
    • low Secrets in code secret-high-entropy-token scripts/bridge-async.js:47
      High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
      usdc: '0x1c…238',
      detector
    • low Secrets in code secret-high-entropy-token scripts/wallet.js:33
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      ? 'EPjF…t1v'
      quoted
    • low Secrets in code secret-high-entropy-token scripts/wallet.js:34
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      : '4zMM…cDU',
      quoted
    • low Secrets in code secret-high-entropy-token scripts/wallet.js:45
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      ? '0x83…913'
      quoted
    • low Secrets in code secret-high-entropy-token scripts/wallet.js:46
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      : '0x03…F7e',
      quoted
    • low Secrets in code secret-high-entropy-token scripts/wallet.js:57
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      ? '0xA0…B48'
      quoted
    • low Risky intent intent-wallet-secrets scripts/wallet.js:68
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)
      throw new Error('Invalid seed phrase format');
      quoted
    • low Risky intent intent-wallet-secrets scripts/wallet.js:109
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (detector / deny-list definition)
      ⚠️  CRITICAL: Save this seed phrase securely!
      detector
    • low Risky intent intent-wallet-secrets scripts/wallet.js:113
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)
      Seed Phrase:
      quoted
    • low Risky intent intent-wallet-secrets scripts/wallet.js:611
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)
      create              Generate new wallet (shows seed phrase once)
      quoted
    • low Risky intent intent-wallet-secrets scripts/wallet.js:631
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)
      WALLET_SEED_PHRASE  Your 12 or 24 word seed phrase
      quoted
    • low Risky intent intent-wallet-secrets SKILL.md:37
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)
      Response: "Add your seed phrase to `.env` as `WALLET_SEED_PHRASE`, then say 'Show my addresses' to verify."
      quoted
    • low Risky intent intent-wallet-secrets SKILL.md:45
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)
      WALLET_SEED_PHRASE="your twelve word seed phrase goes here"
      quoted
    • low Risky intent intent-wallet-secrets SKILL.md:66
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (detector / deny-list definition)
      ⚠️  CRITICAL: Save this seed phrase securely!
      detector
    • low Risky intent intent-wallet-secrets test-bridge.js:11
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (test fixture / example file)
      // Derive private key from seed phrase
      fixture

    Files scanned: 15. 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

    • 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
    • 30Running it twice. 5 mutating operations with no state check
    • 40Consistency. Frontmatter name (agent-wallet) differs from the folder (agent-wallet-usdc)
    • 50Failures and branches. 0 branches, has a failure section
    • 60Tools and files. Uses tools (node) that frontmatter does not declare
    • 60Result and completion. Output format stated, no completion criterion
    • 100Steps. 16 steps
    • 100Execution cost. Instruction body is 1132 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 (5 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

    • +4Description does not say when NOT to use the skill (false activations)
    • -31 of 2 scripts are never mentioned in SKILL.md
    • +1No license
    • +2Single-language instructions
    • +5Description quotes 6 example trigger phrases
    • +3Description length 370: enough signal without eating the budget
    • +4Structure: 17 headings
    • +3Step-by-step instructions: 16 items
    • +3Output format is stated explicitly
    • +4Has examples (4 code blocks)
    • +4Reference files are cited in the instructions (1 of 1)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 93.

    External checks

    ClawHub: suspicious
    This is a real wallet skill, but it gives an agent direct authority to move crypto funds with limited built-in safeguards.
    LLM: suspicious (high) · VirusTotal: suspicious · 28 May 2026