BB openbroker
Hyperliquid trading plugin with background position monitoring and custom automations. Execute market orders, limit orders, manage positions, view funding rates, run trading strategies, and write event-driven automation scripts with automatic alerts for PnL changes and liquidation risk.
As a process B 65/100 · Nearly there — weak spots: result and completion, inputs and preconditions, execution cost
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 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.
How to improve
- 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 · 3
✓ No critical or high findings
Medium and low: 3
-
medium Risky intent
intent-wallet-secretsskill-card.md:25Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer targetRisk: The skill can give an agent real-money trading authority through a wallet private key and live Hyperliquid order commands.
-
medium Risky intent
intent-wallet-secretsSKILL.md:149Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer targetHYPERLIQUID_PRIVATE_KEY=0x... # API wallet private key
-
medium Risky intent
intent-wallet-secretsSKILL.md:491Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target| `HYPERLIQUID_PRIVATE_KEY` | Yes | Wallet private key (0x...) |
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 14695 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 65/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 40Execution cost. Instruction body is 14695 tokens: crowds the task out of the window
- 50When it triggers. No condition that starts the skill
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 96 steps
- 100Failures and branches. 10 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 13 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (26 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
- +2Single-language instructions
- +3Description length 287: enough signal without eating the budget
- +4Structure: 84 headings
- +3Step-by-step instructions: 96 items
- +4Has examples (58 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 72.