SKILLEMALL.ai
GitHub ↗ RU Sign in

DC wayfinder

DeFi trading, yield strategies, and portfolio management via the Wayfinder Paths CLI (`poetry run wayfinder`). Use when the user wants to check balances, swap tokens, bridge assets, trade perps, trade prediction markets (Polymarket), run automated yield strategies (stablecoin yield, basis trading, Moonwell loops, HyperLend, Boros HYPE), manage wallets, discover DeFi pools, look up token metadata, manage LP positions (Uniswap V3 / ProjectX), or execute one-off DeFi scripts. Supports Ethereum, Base, Arbitrum, Polygon, BSC, Avalanche, Plasma, and HyperEVM via protocol adapters.

Not recommendedlow grade D
ClawHub Agent Skills author: canuc v0.0.4 19 files · 1 script body ≈ 13 392 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process C 58/100 · Has gaps — weak spots: result and completion, inputs and preconditions, execution cost

ProcedureGitHubSoftware developmentAI 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
55/100
safety, quality, tests
Safety 60%
42
Quality 40%
75
Run on models
none yet
Process rating
C
58/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Execution cost w 6
40
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

  1. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
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 · 26

✓ No critical or high findings

Medium and low: 26
  • medium Risky intent intent-wallet-secrets references/setup.md:60
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
    ## Bot Wallets (Prefer Seed Phrase)
  • medium Risky intent intent-wallet-secrets references/setup.md:62
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
    `scripts/setup.py` creates **random local dev wallets** by default (it writes `private_key_hex` into `config.json`). For a long-running bot, prefer a **single seed phrase** stored in your backend/secr
  • medium Risky intent intent-wallet-secrets references/setup.md:67
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
    - Ask the user to **retrieve the seed phrase directly from their machine or secret manager** (recommended), if one already exists. Tell them where/how:
  • medium Risky intent intent-wallet-secrets references/setup.md:70
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
    3. Fetch the seed phrase from your secret manager (avoid printing/logging it).
  • medium Risky intent intent-wallet-secrets references/setup.md:72
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
    - **Only if the user explicitly confirms they cannot access the machine to retrieve it themselves**, offer to generate a new seed phrase and display it once for the user to record, then store it in th
  • medium Risky intent intent-wallet-secrets SKILL.md:72
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
    - For a long-running bot, prefer a seed phrase stored in your backend/secret manager rather than generating random wallets on the server.
  • medium Risky intent intent-wallet-secrets SKILL.md:73
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
    - On first-time setup, the user should retrieve the seed phrase directly from their machine or secret manager. Only offer to display the seed phrase if the user explicitly confirms they cannot access
  • medium Risky intent intent-wallet-secrets SKILL.md:683
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
    - **NEVER output private keys or seed phrases into the conversation.** These are secrets that must stay on the machine. Only offer to display a seed phrase if the user explicitly confirms they cannot
  • low Secrets in code secret-high-entropy-token references/adapters.md:160
    High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
    | USDC | `0xEd…c22` | `0x83…913` |
    table
  • low Secrets in code secret-high-entropy-token references/adapters.md:161
    High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
    | WETH | `0x62…457` | `0x42…006` |
    table
  • low Secrets in code secret-high-entropy-token references/adapters.md:162
    High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
    | wstETH | `0x62…04b` | `0xc1…452` |
    table
  • low Secrets in code secret-high-entropy-token references/coding-interface.md:119
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    token_address="0x83…913",  # USDC
    quoted
  • low Secrets in code secret-high-entropy-token references/coding-interface.md:172
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    USDC_MTOKEN = "0xEd…c22"
    quoted
  • low Secrets in code secret-high-entropy-token references/coding-interface.md:173
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    WETH_MTOKEN = "0x62…457"
    quoted
  • low Secrets in code secret-high-entropy-token references/coding-interface.md:335
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    USDC_MTOKEN = "0xEd…c22"
    quoted
  • low Secrets in code secret-high-entropy-token references/coding-interface.md:336
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    WETH_MTOKEN = "0x62…457"
    quoted
  • low Secrets in code secret-high-entropy-token references/hyperliquid.md:74
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    - This repo’s constant: `ARBITRUM_USDC_ADDRESS = 0xaf…831`
    quoted
  • low Secrets in code secret-high-entropy-token references/hyperliquid.md:76
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    - This repo’s constant: `HYPERLIQUID_BRIDGE_ADDRESS = 0x2D…dF7`
    detector
  • low Secrets in code secret-high-entropy-token references/hyperliquid.md:289
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    Builder attribution uses a fixed wallet `0xaA…65c`. Fee value `f` is in **tenths of a basis point** (e.g. `30` = 0.030%). Set in `config.json` under `strategy.builder
    quoted
  • low Secrets in code secret-high-entropy-token references/moonwell.md:54
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    USDC_MTOKEN = "0xEd…c22"
    quoted
  • low Secrets in code secret-high-entropy-token references/moonwell.md:55
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    BASE_USDC = "0x83…913"
    quoted
  • low Secrets in code secret-high-entropy-token references/moonwell.md:82
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    - **Two USDC markets on Base**: Main: `0xEd…c22` (use this). Secondary: `0x70…cC8`.
    quoted
  • low Secrets in code secret-high-entropy-token references/pendle.md:82
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    token_in="0x83…913",  # USDC
    quoted
  • low Secrets in code secret-high-entropy-token references/polymarket.md:57
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    - **USDC vs USDC.e (collateral mismatch):** Polymarket trading collateral is **USDC.e** on Polygon (`0x27…174`, 6 decimals), not native Polygon USDC (`0x3c…EF5
    detector
  • low Secrets in code secret-high-entropy-token references/strategies.md:60
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    - **Collateral Token (Arbitrum)**: LayerZero OFT HYPE at `0x00…Dc1`
    quoted
  • low Secrets in code secret-high-entropy-token references/tokens-and-pools.md:24
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    Example: `base…913`
    quoted

Files scanned: 19. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 13392 tokens (recommended < 5000); move details to references/

Process rating: all ten parameters 58/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 40Execution cost. Instruction body is 13392 tokens: crowds the task out of the window
  • 60Tools and files. Uses tools (bash, web, git, python, node) that frontmatter does not declare
  • 70When it triggers. States when to use, but not when not to
  • 85Steps. 98 steps, 1 vague phrases
  • 100Failures and branches. 8 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Running it twice. Mutating operations check current state
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 14 top-level sections: this looks like several domains in one skill
  • low The skill ranks results itself: that belongs to the system behind the tool, not the model
  • low The response is described with custom markup (14 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 2 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +3Description length 581: enough signal without eating the budget
  • +4Structure: 49 headings
  • +3Step-by-step instructions: 98 items
  • +4Has examples (31 code blocks)
  • +4Reference files are cited in the instructions (14 of 14)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.

External checks

ClawHub: suspicious
Wayfinder is a disclosed DeFi automation skill, but it needs Review because it can use local private keys to run live fund-moving trades, transfers, strategies, and scripts.
LLM: suspicious (high) · VirusTotal: suspicious · 28 May 2026