BD web3-trader
DEX swap 交易技能。当用户提到 swap、兑换、卖出、买入、换成 USDT、交易 ETH、DEX 交易、代币兑换、token swap、sell ETH、buy USDT、交易代币、限价单、limit order、挂单、永续合约、perpetual、开多、开空、做多、做空、杠杆、leverage、止盈、止损、Hyperliquid、平仓、close position、查持仓、funding rate、资金费率、风控、risk control 等关键词时激活。v1 通过 Antalpha AI DEX 聚合器做即时 Swap；v2 新增 Hyperliquid CLOB 限价单、永续合约、Agent Wallet 零托管签名。v2.0.1 新增三级风控确认、余额预检、订单修改、下单失败容错。支持 MetaMask/OKX/Trust/TokenPocket 四大钱包。零托管，私钥不离开用户钱包。
As a process D 42/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
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.
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.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The purpose itself is risky: wallets, browser password stores, offensive security. Even an honest implementation gives the agent access to things that cost money.
Explain in the description why the access is needed and how it is limited; add tests that show refusals on dangerous requests.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
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".
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
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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 · 7
✓ No critical or high findings
Medium and low: 7
-
medium Dangerous commands
cmd-pipe-to-shellinstall.sh:3Downloads and executes remote code from an unrecognised host (pipe to shell) (code comment)# Usage: curl -fsSL install.sh | bash
comment -
medium Risky intent
intent-wallet-secretsskill-card.md:21Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer targetMitigation: Review carefully before installing, start with test or very small balances, treat any agent key as a live trading credential, and avoid using a main wallet private key. <br>
-
medium Exfiltration
net-redirectable-api-keysrc/service/web3-trader.config.ts:13Helper sends the API key to a host configured by an environment variable — the key can be redirected to another serverAPI key + configurable base URL from environment
-
low Secrets in code
secret-high-entropy-tokenSKILL.md:131High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)"taker": "0x81…1Dd"
quoted -
low Exfiltration
net-credential-usesrc/service/smart-swap-page.service.ts:476Credential used in a network call (verify the destination is the intended service) (quoted — discussed, not commanded)<button class="confirm-btn step-btn" id="approveBtn" onclick="doApprove()">⚡ APPROVE ${sellToken}</button>quoted -
low Secrets in code
secret-high-entropy-tokensrc/service/smart-swap.service.ts:11High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)const INCH_ROUTER = "0x11…a65";
quoted -
low Secrets in code
secret-high-entropy-tokensrc/tools/web3-trader.tools.ts:631High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)router_contract: "0x11…a65",
quoted
Files scanned: 28. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
body-longSKILL.md body ≈ 5595 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 42/100
- 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. 5 mutating operations with no state check
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 70Execution cost. Instruction body is 5595 tokens
- 100Steps. 107 steps
- 100Consistency. Name and required fields are in place
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 17 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (7 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
- -2localhost URLs: will not work for another user
- -2104 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +3Description length 406: enough signal without eating the budget
- +4Structure: 59 headings
- +3Step-by-step instructions: 107 items
- +4Has examples (21 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
- +3All 6 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 65.