SKILLEMALL.ai
RU Sign in

BC bank-skill

Traditional banking via Wise API + on-chain token swaps on Base

ClawHub Agent Skills author: singularityhacker v1.0.1 29 files · 1 script body ≈ 2 232 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

As a process C 62/100 · Has gaps — weak spots: result and completion, consistency, running it twice

IntegrationInfrastructuretype 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
78/100
safety, quality, tests
Safety 60%
77
Quality 40%
80
Run on models
none yet
Process rating
C
62/100
Has gaps
Result and completion w 14
0
Progress reporting w 2
0
Running it twice w 4
30
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 · 15

    ✓ No critical or high findings

    Medium and low: 15
    • medium Risky intent intent-wallet-secrets README.md:55
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
      | `CLAWBANK_WALLET_PASSWORD` | No | Sweeper wallet keystore password (default: clawbank-default) |
    • medium Risky intent intent-wallet-secrets SKILL.md:22
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
      - Optional: `CLAWBANK_WALLET_PASSWORD` (wallet keystore password, defaults to "clawbank-default")
    • low Secrets in code secret-high-entropy-token bankskills/sweeper.py:17
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      UNIVERSAL_ROUTER_ADDRESS = "0x6f…b43"
      quoted
    • low Secrets in code secret-high-entropy-token bankskills/sweeper.py:26
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      CLAWBANK_HOOKS = "0xb4…8CC"
      quoted
    • low Secrets in code secret-high-entropy-token bankskills/sweeper.py:329
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      V3_ROUTER = "0x3f…FAD"
      quoted
    • low Secrets in code secret-high-entropy-token bankskills/sweeper.py:479
      High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
      CLAWBANK_ADDRESS = "0x16…B07"
      detector
    • low Risky intent intent-wallet-secrets bankskills/wallet.py:84
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)
      """Export the wallet private key for manual recovery or import into MetaMask.
      quoted
    • low Secrets in code secret-high-entropy-token README.md:157
      High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
      "Set target token to 0x83…913"  (USDC)
      detector
    • low Secrets in code secret-high-entropy-token README.md:304
      High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
      set_target_token("0x83…913")  # USDC
      detector
    • low Secrets in code secret-high-entropy-token README.md:307
      High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
      set_target_token("0x16…B07")  # ClawBank
      detector
    • low Secrets in code secret-high-entropy-token README.md:466
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      - `token_address` — ERC-20 contract address on Base (e.g., "0x83…913" for USDC)
      quoted
    • low Secrets in code secret-high-entropy-token README.md:502
      High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
      set_target_token("0x83…913")  # USDC
      detector
    • low Secrets in code secret-high-entropy-token SKILL.md:202
      High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
      echo '{"action": "set-target-token", "tokenAddress": "0x83…913"}' | ./run.sh
      detector
    • low Secrets in code secret-high-entropy-token SKILL.md:227
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      echo '{"action": "get-token-balance", "tokenAddress": "0x83…913"}' | ./run.sh
      quoted
    • low Secrets in code secret-high-entropy-token SKILL.md:260
      High-entropy token-like string (may be an id, hash or a credential) (placeholder value)
      echo '{"action": "send-token", "tokenAddress": "0x83…913", "toAddress": "0x...", "amount": 5.0}' | ./run.sh
      placeholder

    Files scanned: 29. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    • note frontmatter-key unknown frontmatter key "homepage"

    Process rating: all ten parameters 62/100

    • 0Result and completion. Does not say what the result is
    • 0Progress reporting. Says nothing while it works
    • 30Running it twice. 17 mutating operations with no state check
    • 40Consistency. Frontmatter name (bank-skill) differs from the folder (bank-skills)
    • 50When it triggers. No condition that starts the skill
    • 50Failures and branches. 0 branches, has a failure section
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 100Tools and files. No external tools needed
    • 100Steps. 62 steps
    • 100Execution cost. Instruction body is 2232 tokens

    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)
    • +3Description length 63: 120–800 characters recommended
    • +3Output format is not stated: the model decides each time
    • +1No license
    • +2Single-language instructions
    • +4Structure: 21 headings
    • +3Step-by-step instructions: 62 items
    • +4Has examples (15 code blocks)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.

    External checks

    ClawHub: suspicious
    This skill is meant for banking and crypto operations, but it can move real funds and expose wallet keys with weak safeguards, so users should review it carefully before installing.
    LLM: suspicious (high) · VirusTotal: suspicious · 10 Sept 2026