SKILLEMALL.ai
GitHub ↗ RU Sign in

BC web3-investor

AI-friendly Web3 investment infrastructure for autonomous agents. Use when (1) discovering and analyzing DeFi/NFT investment opportunities, (2) executing secure transactions via Safe Vault mechanism, (3) managing portfolio with dashboards and expiry alerts. Supports ETH mainnet, MetaMask & Safe{Wallet}, configurable risk preferences and whitelist protection.

modbender/skill-library-mcp Agent Skills author: modbender MIT 22 files body ≈ 3 013 tokens Open the sourcegithub.com↗ analyzed 3 d ago

AI-friendly Web3 investment infrastructure for autonomous agents.

As a process C 63/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

IntegrationData and analyticsAI 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
77/100
safety, quality, tests
Safety 60%
74
Quality 40%
81
Run on models
none yet
Process rating
C
63/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
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 · 22

    ✓ No critical or high findings

    Medium and low: 22
    • medium Risky intent intent-wallet-secrets SKILL.md:192
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
      # Required for Phase 2+: Wallet private key
    • low Secrets in code secret-high-entropy-token config/protocols.json:8
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      "primary_contract": "0x87…4E2",
      quoted
    • low Secrets in code secret-high-entropy-token config/protocols.json:26
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      "primary_contract": "0x87…4E2",
      quoted
    • low Secrets in code secret-high-entropy-token config/protocols.json:34
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      "primary_contract": "0xc3…dc3",
      quoted
    • low Secrets in code secret-high-entropy-token config/protocols.json:52
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      "primary_contract": "0xc3…dc3",
      quoted
    • low Secrets in code secret-high-entropy-token config/protocols.json:60
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      "primary_contract": "0xae…E84",
      quoted
    • low Secrets in code secret-high-entropy-token references/protocols.md:8
      High-entropy token-like string (may be an id, hash or a credential)
      - **Contract**: 0x87…4E2
    • low Secrets in code secret-high-entropy-token references/protocols.md:16
      High-entropy token-like string (may be an id, hash or a credential)
      - **Contract**: 0xc3…dc3
    • low Secrets in code secret-high-entropy-token references/protocols.md:34
      High-entropy token-like string (may be an id, hash or a credential)
      - **Contract**: 0xae…E84
    • low Secrets in code secret-high-entropy-token references/protocols.md:42
      High-entropy token-like string (may be an id, hash or a credential)
      - **Contract**: 0xae…393
    • low Secrets in code secret-high-entropy-token references/protocols.md:52
      High-entropy token-like string (may be an id, hash or a credential)
      - **Factory**: 0x1F…984
    • low Secrets in code secret-high-entropy-token references/safe-vault-spec.md:84
      High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)
      "to": "0x87…4E2",
      fixturequoted
    • low Secrets in code secret-high-entropy-token references/safe-vault-spec.md:159
      High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)
      "address": "0x87…4E2",
      fixturequoted
    • low Risky intent intent-offensive-security references/safe-vault-spec.md:181
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (test fixture / example file)
      - Bug bounty program
      fixture
    • low Secrets in code secret-high-entropy-token scripts/discovery/dune_mcp.py:23
      High-entropy token-like string (may be an id, hash or a credential) (placeholder value)
      DUNE_API_KEY = "v9j8…uCI"  # TODO: Move to env variable
      placeholder
    • low Secrets in code secret-high-entropy-token scripts/trading/safe_vault.py:56
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      "USDC": "0xA0…B48",
      quoted
    • low Secrets in code secret-high-entropy-token scripts/trading/safe_vault.py:57
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      "USDT": "0xdA…ec7",
      quoted
    • low Secrets in code secret-high-entropy-token scripts/trading/safe_vault.py:58
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      "DAI": "0x6B…d0F",
      quoted
    • low Secrets in code secret-high-entropy-token scripts/trading/safe_vault.py:59
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      "WETH": "0xC0…Cc2",
      quoted
    • low Secrets in code secret-high-entropy-token scripts/trading/safe_vault.py:60
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      "stETH": "0xae…E84",
      quoted
    • low Secrets in code secret-high-entropy-token SKILL.md:236
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      **Address**: `0x1F…a3e`
      quoted
    • low Secrets in code secret-high-entropy-token SKILL.md:486
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      **地址**: `0x1F…a3e`
      quoted

    Files scanned: 22. 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 63/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 20When it triggers. No condition that starts the skill
    • 30Running it twice. 1 mutating operations with no state check
    • 100Tools and files. No external tools needed
    • 100Steps. 82 steps
    • 100Failures and branches. 1 branches, has a failure section
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 3013 tokens
    • 100Progress reporting. Reports progress
    • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
    • low 21 top-level sections: this looks like several domains in one skill

    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
    • -5TODO / placeholder text left in the skill
    • -217 emoji in the instructions: noise for the model
    • +1No license
    • +2Single-language instructions
    • +3Description length 360: enough signal without eating the budget
    • +4Structure: 57 headings
    • +3Step-by-step instructions: 82 items
    • +4Has examples (15 code blocks)
    • +4Reference files are cited in the instructions (4 of 4)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.