SKILLEMALL.ai

CC solana-copy-trader

Solana whale copy trading bot. Track any wallet, copy trades in real-time via Jupiter + Pump.fun APIs, with paper trading simulation and live execution. Use when user wants to copy trade a Solana wallet, track whale transactions, scan for arbitrage opportunities, monitor pump.fun token launches, or set up an autonomous Solana trading bot.

ClawHub Agent Skills author: YouthAIAgent v1.0.0 15 files body ≈ 702 tokens Open the sourceclawhub.ai analyzed 3 d ago

As a process C 54/100 · Has gaps — weak spots: result and completion, when it triggers, failures and branches

ProcedureInfrastructuretype and topics are labelled automatically from the skill text
JSON
Technical rating
C
74/100
safety, quality, tests
Safety 60%
63
Quality 40%
91
Run on models
none yet
Process rating
C
54/100
Has gaps
Result and completion w 14
0
Failures and branches w 10
0
Progress reporting w 2
0
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.

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.

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 · 25

    ✓ No critical or high findings

    Medium and low: 25
    • medium Exfiltration net-credential-use scripts/src/price_monitor.js:34
      Credential used in a network call (verify the destination is the intended service)
      const res = await axios.get(`${JUPITER_PRICE_API}?ids=${tokenMint}`, {
    • medium Risky intent intent-wallet-secrets scripts/src/sniper.js:193
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
      * Real execution ke liye wallet private key chahiye
    • medium Risky intent intent-wallet-secrets scripts/src/sniper.js:257
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
      // Requires: wallet private key + enough SOL
    • low Exfiltration exfil-webhook-url references/api-setup.md:14
      Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
      4. Get chat ID: `https://api.telegram.org/bot<TOKEN>/getUpdates`
      placeholder
    • low Exfiltration exfil-webhook-url scripts/src/alerts.js:12
      Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
      `https://api.telegram.org/bot${config.botToken}/sendMessage`,
      placeholder
    • low Secrets in code secret-high-entropy-token scripts/src/arbitrage.js:36
      High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
      'EPjF…t1v', // USDC
      detector
    • low Secrets in code secret-high-entropy-token scripts/src/arbitrage.js:37
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      'Es9v…NYB',  // USDT
      quoted
    • low Secrets in code secret-high-entropy-token scripts/src/arbitrage.js:38
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      'mSoL…7So',  // mSOL
      quoted
    • low Secrets in code secret-high-entropy-token scripts/src/arbitrage.js:39
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      'DezX…263', // BONK
      quoted
    • low Secrets in code secret-high-entropy-token scripts/src/arbitrage.js:40
      High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
      'JUPy…vCN',  // JUP
      detector
    • low Secrets in code secret-password-literal scripts/src/config.js:33
      Hard-coded password / key literal (may be an example)
      const secretKey = bs58…ode(process.env.PRIVATE_KEY);
    • low Secrets in code secret-high-entropy-token scripts/src/config.js:50
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      JUPITER:    'JUP6…aV4',
      quoted
    • low Secrets in code secret-high-entropy-token scripts/src/config.js:51
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      RAYDIUM:    '675k…Mp8',
      quoted
    • low Secrets in code secret-high-entropy-token scripts/src/config.js:52
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      ORCA:       'whir…yCc',
      quoted
    • low Secrets in code secret-high-entropy-token scripts/src/config.js:53
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      PUMP_FUN:   '6EF8…F6P',
      quoted
    • low Secrets in code secret-high-entropy-token scripts/src/config.js:54
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      METEORA:    'Eo7W…3Rn',
      quoted
    • low Secrets in code secret-high-entropy-token scripts/src/copy_trade.js:24
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      const WHALE = 'AgmL…N51';
      quoted
    • low Secrets in code secret-high-entropy-token scripts/src/copy_trade.js:31
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      'So11…112',
      quoted
    • low Secrets in code secret-high-entropy-token scripts/src/sniper.js:30
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      const PUMP_FUN_PROGRAM = '6EF8…F6P';
      quoted
    • low Secrets in code secret-high-entropy-token scripts/src/sniper.js:32
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      const RAYDIUM_POOL_PROGRAM = '675k…Mp8';
      quoted
    • low Secrets in code secret-high-entropy-token scripts/src/tracker_api.js:13
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      const WHALE = 'AgmL…N51';
      quoted
    • low Secrets in code secret-high-entropy-token scripts/src/wallet_tracker.js:15
      High-entropy token-like string (may be an id, hash or a credential)
      * AgmL…N51
    • low Secrets in code secret-high-entropy-token scripts/src/wallet_tracker.js:24
      High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
      const WHALE_WALLET = 'AgmL…N51';
      detector
    • low Exfiltration read-dotenv SKILL.md:19
      Reads a .env file
      cp .env.example .env  # fill in keys
    • low Secrets in code secret-high-entropy-token SKILL.md:95
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      Default whale: `AgmL…N51`
      quoted

    Files scanned: 15. 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 54/100

    • 0Result and completion. Does not say what the result is
    • 0Failures and branches. Linear process with no failure handling
    • 0Progress reporting. Says nothing while it works
    • 20When it triggers. No condition that starts the skill
    • 60Tools and files. Uses tools (node) that frontmatter does not declare
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 100Steps. 17 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 702 tokens
    • 100Running it twice. No mutating operations
    • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing

    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 340: enough signal without eating the budget
    • +4Structure: 10 headings
    • +3Step-by-step instructions: 17 items
    • +4Has examples (4 code blocks)
    • +4Reference files are cited in the instructions (2 of 2)
    • +3All 1 scripts are documented

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.

    External checks

    ClawHub: suspicious
    This is a disclosed Solana trading bot, but live mode can use a raw private key to automatically sign real swaps until stopped.
    LLM: suspicious (high) · VirusTotal: suspicious · 28 May 2026