BF liquid-agent-stocks
Buy, hold, rebalance and sell a basket of Coinbase tokenized US stocks (NVDA, AAPL, META, GOOGL) on Base from $1 through the free Liquid Agent API. Use when a user asks to invest in stocks, buy an index or ETF on-chain, put USDC into equities, check or rebalance a stock portfolio, or cash out of stocks.
Buy, hold, rebalance and sell a basket of Coinbase tokenized US stocks (NVDA, AAPL, META, GOOGL) on Base from $1 through the free Liquid Agent API.
As a process F 48/100 · Will not run — References files that are not bundled: examples/gasless.js
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 text references files that are not there: add them or drop the references.
- 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 · 2
✓ No critical or high findings
Medium and low: 2
-
medium Risky intent
intent-wallet-secretsSKILL.md:83Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target- Never send a private key or seed phrase anywhere. This API never asks for one; it only returns data for you to sign locally.
-
low Secrets in code
secret-high-entropy-tokenSKILL.md:32High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)- **USDC on Base** for the purchase (min $1, 0.20% mint fee). USDC is `0x83…913`.
quoted
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: examples/gasless.js - note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 48/100
- 0Tools and files. 1 referenced file(s) missing: examples/gasless.js
- 0Result and completion. Does not say what the result is
- 20When it triggers. No condition that starts the skill
- 30Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 12 mutating operations with no state check
- 100Steps. 30 steps
- 100Failures and branches. 3 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1704 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low The response is described with custom markup (4 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
- +1No license
- +2Single-language instructions
- +3Description length 304: enough signal without eating the budget
- +4Structure: 7 headings
- +3Step-by-step instructions: 30 items
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 77.