SKILLEMALL.ai
GitHub ↗ RU Sign in

DC yieldvault-agent

Autonomous yield farming agent for BNB Chain with deterministic execution, smart contract integration, and automated decision-making.

Not recommendedlow grade D
modbender/skill-library-mcp Agent Skills author: modbender MIT 50 files body ≈ 959 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Autonomous yield farming agent for BNB Chain with deterministic execution, smart contract integration, and automated decision-making.

As a process C 55/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

IntegrationTelegramAI 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%
43
Quality 40%
72
Run on models
none yet
Process rating
C
55/100
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

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
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 · 53

✓ No critical or high findings

Medium and low: 53
  • medium Risky intent intent-wallet-secrets tx-executor.js:4
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
    * Signs transactions with wallet private key and handles confirmations
  • low Secrets in code secret-high-entropy-token config.deployed.json:12
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "address": "0x58…76b",
    quoted
  • low Secrets in code secret-high-entropy-token config.deployed.json:13
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "underlying": "0x8b…A72",
    quoted
  • low Secrets in code secret-high-entropy-token config.deployed.json:21
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "address": "0x6E…df0",
    quoted
  • low Secrets in code secret-high-entropy-token config.deployed.json:30
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "address": "0x0C…4E4",
    quoted
  • low Secrets in code secret-high-entropy-token config.deployed.json:31
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "underlying": "0x84…b06",
    quoted
  • low Secrets in code secret-high-entropy-token contracts/ABI_USAGE.md:79
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "token": "0xB4…312",
    quoted
  • low Secrets in code secret-high-entropy-token contracts/deploy.js:118
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    'vaul…001': '0xB4…312', // USDC on testnet
    quoted
  • low Secrets in code secret-high-entropy-token contracts/deploy.js:119
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    'vaul…001': '0x8b…A72', // WETH on testnet
    quoted
  • low Secrets in code secret-high-entropy-token contracts/deploy.js:120
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    'vaul…001': '0x83…c63', // CAKE on testnet
    quoted
  • low Secrets in code secret-high-entropy-token contracts/deploy.js:121
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    'vaul…001': '0xB4…312', // USDC on testnet
    quoted
  • low Secrets in code secret-high-entropy-token contracts/deploy.js:122
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    'vaul…001': '0x7a…E1F', // Mock WBTC
    quoted
  • low Exfiltration read-dotenv contracts/DEPLOYMENT_SUMMARY.md:84
    Reads a .env file
    cp .env.example .env
  • low Exfiltration read-dotenv contracts/DEPLOYMENT.md:91
    Reads a .env file
    cp .env.example .env
  • low Secrets in code secret-high-entropy-token contracts/DEPLOYMENT.md:189
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    const underlyingToken = "0xB4…312"; // USDC testnet
    quoted
  • low Secrets in code secret-high-entropy-token contracts/DEPLOYMENT.md:242
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    arguments: ['vaul…001', '0xB4…312']
    detector
  • low Secrets in code secret-high-entropy-token contracts/DEPLOYMENT.md:274
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    npx hardhat verify --network bnbTestnet <CONTRACT_ADDRESS> "vaul…001" "0xB4…312"
    quoted
  • low Secrets in code secret-high-entropy-token contracts/DEPLOYMENT.md:354
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "token": "0xB4…312",
    quoted
  • low Exfiltration read-dotenv contracts/DEPLOYMENT.md:383
    Reads a .env file
    cat .env | grep PRIVATE_KEY
  • low Secrets in code secret-high-entropy-token contracts/deployments.json:5
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "address": "0x58…76b",
    quoted
  • low Secrets in code secret-high-entropy-token contracts/deployments.json:6
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "token": "0x8b…A72",
    quoted
  • low Secrets in code secret-high-entropy-token contracts/deployments.json:15
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "address": "0x6E…df0",
    quoted
  • low Secrets in code secret-high-entropy-token contracts/deployments.json:25
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "address": "0x0C…4E4",
    quoted
  • low Secrets in code secret-high-entropy-token contracts/deployments.json:26
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "token": "0x84…b06",
    quoted
  • low Exfiltration read-dotenv contracts/QUICKSTART.txt:12
    Reads a .env file
    cp .env.example .env
  • low Exfiltration read-dotenv contracts/QUICKSTART.txt:226
    Reads a .env file
    ☐ Copy .env.example to .env
  • low Exfiltration read-dotenv contracts/README.md:50
    Reads a .env file
    cp .env.example .env
  • low Secrets in code secret-high-entropy-token contracts/README.md:156
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "0xB4…312" // USDC testnet
    quoted
  • low Secrets in code secret-high-entropy-token contracts/README.md:365
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "0xB4…312"
    quoted
  • low Secrets in code secret-high-entropy-token contracts/scripts/deploy.js:10
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    token: "0xB4…312", // USDC testnet
    quoted
  • low Secrets in code secret-high-entropy-token contracts/scripts/deploy.js:14
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    token: "0x8b…A72", // WETH testnet
    quoted
  • low Secrets in code secret-high-entropy-token contracts/scripts/deploy.js:18
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    token: "0x83…c63", // CAKE testnet
    quoted
  • low Secrets in code secret-high-entropy-token contracts/scripts/deploy.js:22
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    token: "0xB4…312", // USDC testnet
    quoted
  • low Secrets in code secret-high-entropy-token contracts/scripts/deploy.js:26
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    token: "0x7a…E1F", // Mock WBTC
    quoted
  • low Secrets in code secret-high-entropy-token contracts/scripts/generate-abi.js:558
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "token": "0xB4…312",
    quoted
  • low Risky intent intent-offensive-security FINAL_CHECKLIST.md:92
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    - Bug bounty program setup
  • low Secrets in code secret-high-entropy-token INTEGRATION_MANIFEST.md:35
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "vaul…001": "0x58…76b",
    quoted
  • low Secrets in code secret-high-entropy-token INTEGRATION_MANIFEST.md:36
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "vaul…001": "0x6E…df0",
    quoted
  • low Secrets in code secret-high-entropy-token INTEGRATION_MANIFEST.md:37
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "vaul…001": "0x0C…4E4"
    quoted
  • low Secrets in code secret-high-entropy-token LIVE_EXECUTION_GUIDE.md:10
    High-entropy token-like string (may be an id, hash or a credential)
    - `vaul…001`: 0x58…76b
  • low Secrets in code secret-high-entropy-token LIVE_EXECUTION_GUIDE.md:11
    High-entropy token-like string (may be an id, hash or a credential)
    - `vaul…001`: 0x6E…df0
  • low Secrets in code secret-high-entropy-token LIVE_EXECUTION_GUIDE.md:12
    High-entropy token-like string (may be an id, hash or a credential)
    - `vaul…001`: 0x0C…4E4
  • low Secrets in code secret-high-entropy-token package-lock.json:97
    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:180
    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 Secrets in code secret-high-entropy-token package-lock.json:334
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…6I6+jvuq…Pqq+JZ0T…Rng==",
    detector
  • low Secrets in code secret-high-entropy-token package-lock.json:354
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…GmY+zPPWTC+wQrp…jmH+yCS3…njA==",
    detector
  • low Secrets in code secret-high-entropy-token package-lock.json:428
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…zbE+oCZYyY+3Zh8…sCw==",
    detector
  • low Secrets in code secret-high-entropy-token QUICK_TEST.md:38
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)
    "vaul…001": "0x58…76b",
    fixturequoted
  • low Secrets in code secret-high-entropy-token QUICK_TEST.md:39
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)
    "vaul…001": "0x6E…df0",
    fixturequoted
  • low Secrets in code secret-high-entropy-token QUICK_TEST.md:40
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)
    "vaul…001": "0x0C…4E4"
    fixturequoted
  • low Secrets in code secret-high-entropy-token test.live.js:20
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)
    const TEST_USER = '0x74…2bE'; // Example address
    fixturequoted
  • low Secrets in code secret-high-entropy-token test.live.js:276
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)
    underlying: '0x8b…A72',
    fixturequoted
  • low Secrets in code secret-high-entropy-token test.live.js:286
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)
    underlying: '0x84…b06',
    fixturequoted

Files scanned: 50. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")

Process rating: all ten parameters 55/100

  • 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. 2 mutating operations with no state check
  • 50Failures and branches. 0 branches, has a failure section
  • 85Steps. 40 steps, 1 vague phrases
  • 100Tools and files. No external tools needed
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 959 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 12 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
  • +1No license
  • +2Single-language instructions
  • +3Description length 133: enough signal without eating the budget
  • +4Structure: 18 headings
  • +3Step-by-step instructions: 40 items
  • +4Has examples (7 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 72.