SKILLEMALL.ai
GitHub ↗ RU Sign in

CD goldenclaw

Manage GoldenClaw (GCLAW) on Solana. Create wallet, claim from faucet, check balance, send tokens, view history. For OpenClaw AI agents.

ClawHub Agent Skills author: GoldenClawOrg v1.0.0 11 files body ≈ 244 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process D 43/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

GeneratorAI 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
C
63/100
safety, quality, tests
Safety 60%
59
Quality 40%
69
Run on models
none yet
Process rating
D
43/100
Unfinished process
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
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.

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 · 17

✓ No critical or high findings

Medium and low: 17
  • medium Risky intent intent-wallet-secrets dist/index.js:9
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
    *   gclaw recover        - Recover wallet from seed phrase
  • medium Risky intent intent-wallet-secrets dist/wallet.js:162
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
    * Your seed phrase can be restored in Phantom to get the same address.
  • medium Risky intent intent-wallet-secrets dist/wallet.js:189
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
    * Uses BIP44 derivation — same as Phantom. Restore your seed phrase in Phantom to get the same address.
  • medium Risky intent intent-wallet-secrets dist/wallet.js:191
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
    * @param mnemonic - The 24-word recovery phrase
  • medium Risky intent intent-wallet-secrets README.md:30
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
    | `gclaw recover <phrase>` | Recover wallet from seed phrase |
  • medium Risky intent intent-wallet-secrets skill-card.md:24
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
    Risk: Wallet recovery and setup involve a BIP39 seed phrase. <br>
  • low Secrets in code secret-high-entropy-token dist/config.js:21
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    exports.GCLAW_TOKEN_MINT = process.env.GCLAW_TOKEN_MINT || '8fUq…r4z';
    quoted
  • low Secrets in code secret-high-entropy-token dist/config.js:54
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    exports.GCLAW_DONATE_ADDRESS = process.env.GCLAW_DONATE_ADDRESS || 'DfMV…4AW';
    quoted
  • low Risky intent intent-wallet-secrets dist/index.js:143
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)
    `🔑 BACKUP SEED PHRASE (SAVE THIS!)`,
    quoted
  • low Risky intent intent-wallet-secrets dist/index.js:150
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)
    `• This seed phrase is Phantom-compatible — restore it in Phantom for the same address`,
    quoted
  • low Risky intent intent-wallet-secrets dist/index.js:151
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)
    `• Never share your seed phrase with anyone`,
    quoted
  • low Risky intent intent-wallet-secrets dist/index.js:162
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)
    return `❌ Please provide your 24-word seed phrase: claw recover <seed phrase>`;
    quoted
  • low Exfiltration net-credential-use dist/index.js:228
    Credential used in a network call (verify the destination is the intended service) (quoted — discussed, not commanded)
    `This amount exceeds the confirmation threshold (${SPENDING_LIMITS.confirmationThreshold} ${TOKEN_SYMBOL}).`,
    quoted
  • low Exfiltration net-credential-use dist/index.js:274
    Credential used in a network call (verify the destination is the intended service) (quoted — discussed, not commanded)
    `Confirmation Threshold: ${SPENDING_LIMITS.confirmationThreshold} ${TOKEN_SYMBOL}`,
    quoted
  • low Secrets in code secret-high-entropy-token dist/onchain-client.js:27
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    exports.DISTRIBUTION_PROGRAM_ID = new web3…Key(process.env.CLAW_DISTRIBUTION_PROGRAM || 'CLAW…111');
    quoted
  • low Risky intent intent-wallet-secrets dist/transactions.js:195
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)
    '  • If you have your 24-word recovery phrase:  gclaw recover "word1 word2 ... word24"',
    quoted
  • low Risky intent intent-wallet-secrets dist/wallet.js:196
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)
    throw new Error('Invalid mnemonic phrase');
    quoted

Files scanned: 11. 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 43/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 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
  • 30Running it twice. 3 mutating operations with no state check
  • 60Tools and files. Uses tools (bash, node) that frontmatter does not declare
  • 100Steps. 15 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 244 tokens

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
  • +4No input/output examples
  • +2Single-language instructions
  • +3Description length 136: enough signal without eating the budget
  • +4Structure: 4 headings
  • +3Step-by-step instructions: 15 items
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 69.

External checks

ClawHub: suspicious
This looks like a real GoldenClaw wallet skill, but it needs review because it auto-runs npm install at startup and can move real Solana assets.
LLM: suspicious (high) · VirusTotal: suspicious · 28 May 2026