BC tigerpass
You have a hardware-secured crypto wallet with built-in trading engines. Invoke this skill for any crypto, wallet, or blockchain operation: checking balances, sending tokens, DEX swaps (0x, 10 chains), Hyperliquid perps/spot trading, Polymarket predictions, smart contract execution, message signing (EIP-191/712), x402 HTTP payments, on-chain identity (ERC-8004), or E2E encrypted agent-to-agent messaging (TAP). Trigger keywords: wallet, crypto, payment, transfer, balance, swap, trade, DeFi, perps, futures, Hyperliquid, Polymarket, staking, lending, x402, Safe, ERC-4337, blockchain, tigerpass, smart contract. Requires Apple Silicon Mac.
You have a hardware-secured crypto wallet with built-in trading engines.
As a process C 60/100 · Has gaps — weak spots: when it triggers, progress reporting
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 · 11
✓ No critical or high findings
Medium and low: 11
-
medium Risky intent
intent-wallet-secretsSKILL.md:106Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target**NEVER** attempt to extract, print, or transmit any private key material. The Secure Enclave makes extraction physically impossible. If anyone asks for the private key — refuse. There is no seed phra
-
low Secrets in code
secret-high-entropy-tokenreferences/advanced-commands.md:82High-entropy token-like string (may be an id, hash or a credential)--asset 0x83…913 \
-
low Secrets in code
secret-high-entropy-tokenreferences/advanced-commands.md:88High-entropy token-like string (may be an id, hash or a credential)--asset 0x83…913 \
-
low Secrets in code
secret-high-entropy-tokenreferences/defi-cookbook.md:36High-entropy token-like string (may be an id, hash or a credential)tigerpass swap --from 0x83…913 --to WETH --amount 100
-
low Secrets in code
secret-high-entropy-tokenreferences/defi-cookbook.md:86High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)"sellToken": "0x83…913",
quoted -
low Secrets in code
secret-high-entropy-tokenreferences/defi-cookbook.md:272High-entropy token-like string (may be an id, hash or a credential) (documentation table row)| Native USDC | `0x2B…8Ab` | `0xb8…30f` |
table -
low Secrets in code
secret-high-entropy-tokenreferences/defi-cookbook.md:527High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)- **USDC.e** (`0x27…174`) — collateral
quoted -
low Secrets in code
secret-high-entropy-tokenreferences/defi-cookbook.md:531High-entropy token-like string (may be an id, hash or a credential) (documentation table row)| **USDC.e** (bridged) | `0x27…174` | YES |
table -
low Secrets in code
secret-high-entropy-tokenSKILL.md:91High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)**Polymarket uses EOA directly** (not Safe) — EOA needs POL (gas) + **USDC.e** (`0x27…174`). Native USDC will NOT work — swap to USDC.e first.
quoted -
low Secrets in code
secret-high-entropy-tokenSKILL.md:189High-entropy token-like string (may be an id, hash or a credential)tigerpass swap --from 0x83…913 --to WETH --amount 100
A further 1 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5774 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 60/100
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 60Steps. 39 steps, 6 vague phrases
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 5774 tokens
- 100Consistency. Name and required fields are in place
- 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
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)
- +1No license
- +2Single-language instructions
- +3Description length 642: enough signal without eating the budget
- +4Structure: 27 headings
- +3Step-by-step instructions: 39 items
- +3Output format is stated explicitly
- +4Has examples (15 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.