FB xaut-trade

Buy or sell XAUT (Tether Gold) on Ethereum. Supports market orders (Uniswap V3) and limit orders (UniswapX). Wallet modes: Foundry keystore or WDK. Delegates non-XAUT intents to registered skills (e.g. Polymarket prediction markets, Hyperliquid trading). Triggers: buy XAUT, XAUT trade, swap USDT for XAUT, sell XAUT, swap XAUT for USDT, limit order, limit buy XAUT, limit sell XAUT, check limit order, cancel limit order, XAUT when, create wallet, setup wallet, polymarket, prediction market, bet on, odds on, hyperliquid, perp, perpetual, long, short, open long, open short, close position, leverage.

Not recommendedcritical or high security findings · low grade F

LeoYeAI/openclaw-master-skills Agent Skills author: LeoYeAI MIT 40 files · 1 script body ≈ 7 244 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Buy or sell XAUT (Tether Gold) on Ethereum.

As a process B 66/100 · Nearly there — weak spots: consistency, progress reporting

Generator Software development Data and analytics AI 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

32/100

safety, quality, tests

Safety 60%: 0
Quality 40%: 79
Run on models: none yet

Process rating

66/100

Nearly there

Progress reporting w 2: 0
Consistency w 8: 40
Tools and files w 18: 60

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.

Dangerous commands

If you install

The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

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

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.
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 · 97

high Dangerous commands cmd-pipe-to-shell references/onboarding.md:171

Downloads and executes remote code from an unrecognised host (pipe to shell)
```
curl -L https://foundry.paradigm.xyz | bash && \
```
high Dangerous commands cmd-pipe-to-shell scripts/setup.sh:189

Downloads and executes remote code from an unrecognised host (pipe to shell)
```
curl -L https://foundry.paradigm.xyz | bash
```

Medium and low: 95

medium Risky intent intent-wallet-secrets README.md:136

Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
```
| `KEYSTORE_PASSWORD_FILE` | Path to keystore password file (**Foundry mode**) | `~/.aurehub/.wallet.password` |
```
medium Dangerous commands cmd-pipe-to-shell README.md:249

Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation table row)
```
| foundry.paradigm.xyz | First setup | Downloads and executes Foundry installer (`curl \| bash`) |
```
table

medium Dangerous commands cmd-pipe-to-shell README.md:255

Downloads and executes remote code from an unrecognised host (pipe to shell) (quoted — discussed, not commanded)

- **Foundry installation** uses `curl | bash`. Review the source at [github.com/foundry-rs/foundry](https://github.com/foundry-rs/foundry) before proceeding. The setup script asks for confirmation bef

quoted

medium Risky intent intent-wallet-secrets references/onboarding.md:109

Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
```
#### Step W3b: Security reminder — back up your seed phrase
```
medium Risky intent intent-wallet-secrets references/onboarding.md:113

Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
```
> **Back up your seed phrase now.**
```

medium Risky intent intent-wallet-secrets references/onboarding.md:115

Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target

> Your wallet is protected by an encrypted vault. If the vault file (`~/.aurehub/.wdk_vault`) or password file (`~/.aurehub/.wdk_password`) is lost or corrupted, **your funds cannot be recovered** wit

medium Risky intent intent-wallet-secrets references/onboarding.md:124

Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
```
> - **Never** save the seed phrase in cloud storage, screenshots, or chat.
```
medium Risky intent intent-wallet-secrets references/onboarding.md:127

Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
```
Do NOT print the seed phrase in the chat. Only provide the export command.
```

medium Risky intent intent-wallet-secrets scripts/lib/export-seed.js:161

Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target

// ── Display seed phrase ──────────────────────────────────────────────────

medium Risky intent intent-wallet-secrets scripts/setup.sh:141

Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target

# ── Security notice: seed phrase backup ──────────────────────────────────────

medium Dangerous commands cmd-pipe-to-shell scripts/setup.sh:178

Downloads and executes remote code from an unrecognised host (pipe to shell) (code comment)
```
# S1: disclose what is about to run before executing curl|bash
```
comment

medium Risky intent intent-wallet-secrets scripts/setup.sh:207

Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target

# ── Step 4: Keystore password file ─────────────────────────────────────────────

medium Risky intent intent-wallet-secrets SKILL.md:43

Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
```
| `KEYSTORE_PASSWORD_FILE` | Path to Foundry keystore password file (mode 0600) | When WALLET_MODE=foundry |
```
medium Risky intent intent-wallet-secrets SKILL.md:71

Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
```
- Seed phrase export is TTY-gated and requires interactive confirmation
```
medium Risky intent intent-wallet-secrets SKILL.md:344

Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
```
> **IMPORTANT: Back up your seed phrase**
```
medium Risky intent intent-wallet-secrets SKILL.md:348

Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
```
> Export your 12-word seed phrase now and store it safely (paper or hardware backup — never in cloud storage or chat).
```
medium Risky intent intent-wallet-secrets SKILL.md:355

Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
```
> Write down the 12 words and keep them offline. **Never share your seed phrase with anyone.**
```
low Secrets in code secret-high-entropy-token config.example.yaml:16

High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)
```
router: "0x68…c45"
```
fixturequoted
low Secrets in code secret-high-entropy-token config.example.yaml:17

High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)
```
quoter: "0x61…21e"
```
fixturequoted
low Secrets in code secret-high-entropy-token config.example.yaml:18

High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)
```
permit2: "0x00…BA3"
```
fixturequoted
low Secrets in code secret-high-entropy-token config.example.yaml:22

High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)
```
address: "0x68…F38"
```
fixturequoted
low Secrets in code secret-high-entropy-token config.example.yaml:25

High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)
```
address: "0xdA…ec7"
```
fixturequoted
low Secrets in code secret-high-entropy-token README.md:213

High-entropy token-like string (may be an id, hash or a credential)
```
0xf3…266 10000000000 \
```
low Secrets in code secret-high-entropy-token README.md:220

High-entropy token-like string (may be an id, hash or a credential)
```
0xf3…266 \
```
low Exfiltration read-dotenv references/balance.md:8

Reads a .env file
```
source ~/.aurehub/.env
```
low Exfiltration read-dotenv references/balance.md:15

Reads a .env file
```
source ~/.aurehub/.env
```
low Exfiltration read-dotenv references/balance.md:31

Reads a .env file
```
source ~/.aurehub/.env
```
low Exfiltration read-dotenv references/balance.md:40

Reads a .env file
```
source ~/.aurehub/.env
```
low Exfiltration read-dotenv references/balance.md:48

Reads a .env file
```
source ~/.aurehub/.env
```

low Exfiltration read-dotenv references/buy.md:3

Reads a .env file (detector / deny-list definition)

All commands below assume CWD is `$SCRIPTS_DIR` and env is sourced. Each Bash block must begin with `source ~/.aurehub/.env` and `cd "$SCRIPTS_DIR"`.

detector

low Exfiltration read-dotenv references/buy.md:14

Reads a .env file
```
source ~/.aurehub/.env
```
low Exfiltration read-dotenv references/buy.md:37

Reads a .env file
```
source ~/.aurehub/.env
```
low Exfiltration read-dotenv references/buy.md:62

Reads a .env file
```
source ~/.aurehub/.env
```
low Exfiltration read-dotenv references/buy.md:93

Reads a .env file
```
source ~/.aurehub/.env
```
low Exfiltration read-dotenv references/limit-order-buy-place.md:14

Reads a .env file
```
source ~/.aurehub/.env
```
low Secrets in code secret-high-entropy-token references/limit-order-buy-place.md:43

High-entropy token-like string (may be an id, hash or a credential)
```
node swap.js allowance --token USDT --spender 0x00…BA3
```
low Secrets in code secret-high-entropy-token references/limit-order-buy-place.md:49

High-entropy token-like string (may be an id, hash or a credential)
```
node swap.js approve --token USDT --amount <AMOUNT_IN> --spender 0x00…BA3
```
low Exfiltration read-dotenv references/limit-order-buy-place.md:63

Reads a .env file
```
source ~/.aurehub/.env
```
low Exfiltration read-dotenv references/limit-order-cancel.md:6

Reads a .env file
```
source ~/.aurehub/.env
```
low Exfiltration read-dotenv references/limit-order-cancel.md:42

Reads a .env file
```
source ~/.aurehub/.env
```
low Exfiltration read-dotenv references/limit-order-sell-place.md:14

Reads a .env file
```
source ~/.aurehub/.env
```
low Secrets in code secret-high-entropy-token references/limit-order-sell-place.md:43

High-entropy token-like string (may be an id, hash or a credential)
```
node swap.js allowance --token XAUT --spender 0x00…BA3
```
low Secrets in code secret-high-entropy-token references/limit-order-sell-place.md:49

High-entropy token-like string (may be an id, hash or a credential)
```
node swap.js approve --token XAUT --amount <AMOUNT_IN> --spender 0x00…BA3
```
low Exfiltration read-dotenv references/limit-order-sell-place.md:63

Reads a .env file
```
source ~/.aurehub/.env
```
low Exfiltration read-dotenv references/limit-order-status.md:6

Reads a .env file
```
source ~/.aurehub/.env
```
low Exfiltration read-dotenv references/onboarding.md:310

Reads a .env file
```
source ~/.aurehub/.env
```
low Exfiltration read-dotenv references/quote.md:10

Reads a .env file
```
source ~/.aurehub/.env
```

low Exfiltration read-dotenv references/sell.md:3

Reads a .env file (detector / deny-list definition)

All commands below assume CWD is `$SCRIPTS_DIR` and env is sourced. Each Bash block must begin with `source ~/.aurehub/.env` and `cd "$SCRIPTS_DIR"`.

detector

low Exfiltration read-dotenv references/sell.md:22

Reads a .env file
```
source ~/.aurehub/.env
```
low Exfiltration read-dotenv references/sell.md:86

Reads a .env file
```
source ~/.aurehub/.env
```
low Exfiltration read-dotenv references/sell.md:109

Reads a .env file
```
source ~/.aurehub/.env
```
low Exfiltration read-dotenv references/sell.md:134

Reads a .env file
```
source ~/.aurehub/.env
```
low Secrets in code secret-high-entropy-token scripts/__tests__/swap-cli.test.js:39

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition; test fixture / example file)
```
const result = parseCliArgs(['allowance', '--token', 'USDT', '--spender', '0x00…BA3']);
```
detectorfixture
low Secrets in code secret-high-entropy-token scripts/__tests__/swap-cli.test.js:42

High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)
```
expect(result.spender).toBe('0x00…BA3');
```
fixturequoted
low Secrets in code secret-high-entropy-token scripts/__tests__/swap-cli.test.js:46

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition; test fixture / example file)
```
const result = parseCliArgs(['approve', '--token', 'USDT', '--amount', '1000', '--spender', '0x00…BA3']);
```
detectorfixture
low Secrets in code secret-high-entropy-token scripts/__tests__/swap-cli.test.js:50

High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)
```
expect(result.spender).toBe('0x00…BA3');
```
fixturequoted
low Secrets in code secret-high-entropy-token scripts/lib/__tests__/config.test.js:46

High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)
```
'    address: "0xdA…ec7"',
```
fixturequoted
low Secrets in code secret-high-entropy-token scripts/lib/__tests__/config.test.js:49

High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)
```
'    address: "0x68…F38"',
```
fixturequoted
low Secrets in code secret-high-entropy-token scripts/lib/__tests__/config.test.js:58

High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)
```
expect(token.address).toBe('0xdA…ec7');
```
fixturequoted
low Secrets in code secret-high-entropy-token scripts/lib/__tests__/config.test.js:66

High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)
```
'    address: "0xdA…ec7"',
```
fixturequoted

…and 35 more

Files scanned: 40. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

warning body-long SKILL.md body ≈ 7244 tokens (recommended < 5000); move details to references/

Process rating: all ten parameters 66/100

0Progress reporting. Says nothing while it works
40Consistency. Frontmatter name (xaut-trade) differs from the folder (aurehub-xaut-trade)
60Tools and files. Uses tools (bash, node) that frontmatter does not declare
60Steps. 142 steps, 5 vague phrases
60Result and completion. Output format stated, no completion criterion
70When it triggers. States when to use, but not when not to
70Inputs and preconditions. Inputs and preconditions are listed
70Execution cost. Instruction body is 7244 tokens
100Failures and branches. 10 branches, has a failure section
100Running it twice. Mutating operations check current state

medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
low 23 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)
-32 of 4 scripts are never mentioned in SKILL.md
+2Single-language instructions
+3Description length 602: enough signal without eating the budget
+4Structure: 41 headings
+3Step-by-step instructions: 142 items
+3Output format is stated explicitly
+4Has examples (22 code blocks)
+4Reference files are cited in the instructions (9 of 12)
+1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.

Tests

— no evals.json

— no spec.yaml

— not run on models

Files · 40

README.md 15K
SKILL.md 29K
SKILL.tests.yaml 12K
_meta.json 1K
config.example.yaml 2K
references/balance.md 3K
references/buy.md 4K
references/limit-order-buy-place.md 5K
references/limit-order-cancel.md 2K
references/limit-order-sell-place.md 5K
references/limit-order-status.md 2K
references/live-trading-runbook.md 4K
references/onboarding.md 13K
references/quote.md 2K
references/sell.md 6K
references/skill-delegation.md 3K
references/wallet-modes.md 1K
scripts/__tests__/helpers.test.js 3K
scripts/__tests__/integration.test.js 1K
scripts/__tests__/swap-cli.test.js 4K
scripts/__tests__/wallet-init.test.js 11K
scripts/helpers.js 1K
scripts/lib/__tests__/config.test.js 3K
scripts/lib/__tests__/create-wallet.test.js 6K
scripts/lib/__tests__/erc20.test.js 3K
scripts/lib/__tests__/provider.test.js 8K
scripts/lib/__tests__/signer.test.js 8K
scripts/lib/__tests__/uniswap.test.js 4K
scripts/lib/config.js 4K
scripts/lib/create-wallet.js 6K
scripts/lib/erc20.js 4K
scripts/lib/export-seed.js 6K
scripts/lib/provider.js 8K
scripts/lib/signer.js 7K
scripts/lib/uniswap.js 5K
scripts/limit-order.js 14K
scripts/package-lock.json 182K
scripts/package.json 1K
scripts/setup.sh 29K
scripts/swap.js 16K

When to use

Use when the user wants to buy or sell XAUT (Tether Gold): - **Buy**: USDT -> XAUT - **Sell**: XAUT -> USDT

Frontmatter

license: MIT

compatibility: Requires Node.js >= 18, Ethereum RPC (HTTPS), and UniswapX API access. Foundry (cast) required only for foundry wallet m

metadata: {"author":"aurehub","version":"2.2.0"}

Dates

In catalog since —

Updated in catalog 20 Jul 2026

First seen here 7 Sept 2026

Last analysis 12 Sept 2026, 13:56 UTC

Last seen in crawl 23 h ago

Score history

Date		Score	Qual.
7 Sept 2026	F	32	79
7 Sept 2026	F	29	73
7 Sept 2026	F	34	84

Similar skills

F xaut-trade ClawHub