SKILLEMALL.ai
GitHub ↗ RU Sign in

CC nadfunagent

Autonomous trading agent for Nad.fun that scans markets, analyzes tokens, executes trades, and distributes profits to MMIND token holders. Uses nadfun-trading, nadfun-indexer, and nadfun-agent-api skills.

Not recommendedcritical or high security findings
modbender/skill-library-mcp Agent Skills author: modbender MIT 21 files body ≈ 12 494 tokens Open the sourcegithub.com↗ analyzed 3 d ago

Autonomous trading agent for Nad.fun that scans markets, analyzes tokens, executes trades, and distributes profits to MMIND token holders. Uses…

As a process C 57/100 · Has gaps — weak spots: result and completion, when it triggers, execution cost

ProcedureTelegramAI and agentsFinancetype 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
C
62/100
safety, quality, tests
Safety 60%
64
Quality 40%
59
Run on models
none yet
Process rating
C
57/100
Has gaps
Result and completion w 14
0
When it triggers w 12
20
Running it twice w 4
30
the three weakest of ten parameters · all ten

What is at stake

The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.

Secrets in code
If you install

The files contain someone else's key or token. If it is live, your agent will call third-party services under a stranger's identity; if it was revoked, the skill's scripts simply fail. Such a key often arrives with the author's whole workspace, personal data included.

For the author

The key is visible to everyone who downloaded the skill and has likely been copied by catalog-scanning bots already. Revoke it now, check bills and access logs, then reissue.

Exfiltration 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 instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

How to improve

  1. Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
  2. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  3. 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 · 15

  • high Secrets in code meta-credential-files .env
    Credential / dotenv files bundled with the skill (1)
    .env
Medium and low: 14
  • medium Exfiltration net-credential-use trading/check-pnl.js:146
    Credential used in a network call (verify the destination is the intended service)
    const mRes = await fetch(`${API_URL}/agent/market/${tokenAddress}`, {
  • low Dangerous commands cmd-cron-mention INSTALL.md:235
    Mentions editing / listing crontab
    crontab -e
  • low Secrets in code secret-high-entropy-token README.md:203
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    **Token Contract**: `0xCe…777` (MMIND)
    quoted
  • low Secrets in code secret-high-entropy-token SKILL.md:771
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    address: '0x7e…7ea', // nad.fun quote contract
    quoted
  • low Secrets in code secret-high-entropy-token trading/buy-token.js:29
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    LENS: '0x7e…7ea',
    quoted
  • low Secrets in code secret-high-entropy-token trading/buy-token.js:30
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    BONDING_CURVE_ROUTER: '0x6F…A22',
    quoted
  • low Secrets in code secret-high-entropy-token trading/buy-token.js:31
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    DEX_ROUTER: '0x0B…137',
    quoted
  • low Secrets in code secret-high-entropy-token trading/buy-token.js:32
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    WMON: '0x3b…33A',
    quoted
  • low Secrets in code secret-high-entropy-token trading/buy-token.js:35
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    LENS: '0xB0…6f1',
    quoted
  • low Secrets in code secret-high-entropy-token trading/check-pnl.js:20
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    const NADFUN_QUOTE_CONTRACT = '0x7e…7ea'; // nad.fun on-chain quote (LENS)
    quoted
  • low Secrets in code secret-high-entropy-token trading/README.md:65
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    LENS is nad.fun’s on-chain quote contract. Signature: `getAmountOut(address token, uint256 amountIn, bool isBuy)`. Mainnet: `0x7e…7ea`.
    detector
  • low Secrets in code secret-high-entropy-token trading/sell-token.js:9
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    LENS: '0x7e…7ea',
    quoted
  • low Secrets in code secret-high-entropy-token trading/sell-token.js:10
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    BONDING_CURVE_ROUTER: '0x6F…A22',
    quoted
  • low Secrets in code secret-high-entropy-token trading/sell-token.js:11
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    DEX_ROUTER: '0x0B…137',
    quoted

Files scanned: 20. 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")
  • warning body-long SKILL.md body ≈ 12494 tokens (recommended < 5000); move details to references/

Process rating: all ten parameters 57/100

  • 0Result and completion. Does not say what the result is
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 19 mutating operations with no state check
  • 40Execution cost. Instruction body is 12494 tokens: crowds the task out of the window
  • 60Tools and files. Uses tools (bash, web, node) that frontmatter does not declare
  • 60Steps. 351 steps, 5 vague phrases
  • 100Inputs and preconditions. Inputs and preconditions are listed
  • 100Failures and branches. 3 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Progress reporting. Reports progress
  • 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

  • +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
  • -32 of 3 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +3Description length 204: enough signal without eating the budget
  • +4Structure: 30 headings
  • +3Step-by-step instructions: 351 items
  • +4Has examples (36 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 59.