CC atxswap
Manage ATX on BSC with wallet creation, price and balance queries, PancakeSwap V3 swaps, liquidity operations, LP positions and holdings, and BNB/ERC20 transfers. Use when the user mentions ATX, BSC, PancakeSwap V3, wallet creation, price checks, buying, selling, liquidity, fees, holdings, LP positions, or token transfers.
As a process C 60/100 · Has gaps — weak spots: result and completion, 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.
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 Dangerous commands
cmd-autorun-instructionSKILL.md:98Instructs the agent to auto-run a script on every sessionFirst run `liquidity.js quote-add` or use `liquidity.js add --base-token ... --amount ...`
-
medium Risky intent
intent-wallet-secretsSKILL.md:140Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target8. Before deleting a wallet, keystore file, or any private-key-bearing wallet
-
medium Risky intent
intent-wallet-secretsSKILL.md:166Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target15. If the user asks to recover, reveal, print, or paste the wallet private key,
-
medium Risky intent
intent-wallet-secretsSKILL.md:413Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target- User asks to delete a wallet, keystore file, or private-key-bearing wallet
-
medium Risky intent
intent-wallet-secretsSKILL.md:420Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target- User asks to recover, reveal, print, or paste a wallet private key in chat
-
low Secrets in code
secret-high-entropy-tokenpackage-lock.json:23High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)"integrity": "sha5…p81+8Ob3…L40/b0i7…gQw==",
detector -
low Secrets in code
secret-high-entropy-tokenpackage-lock.json:85High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)"integrity": "sha512-+lF0B…kdX+94aG…d8c+B3KT…U6A==",
detector -
low Secrets in code
secret-high-entropy-tokenpackage-lock.json:212High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)"integrity": "sha5…CzX+oOPq…N14+GARU…vzg==",
detector -
low Secrets in code
secret-high-entropy-tokenscripts/liquidity.js:159High-entropy token-like string (may be an id, hash or a credential)function huma…en0(h, isAtxToken0) { -
low Secrets in code
secret-high-entropy-tokenscripts/liquidity.js:170High-entropy token-like string (may be an id, hash or a credential)const rawA = huma…en0(minHuman, isAtxToken0);
-
low Secrets in code
secret-high-entropy-tokenscripts/liquidity.js:171High-entropy token-like string (may be an id, hash or a credential)const rawB = huma…en0(maxHuman, isAtxToken0);
Files scanned: 15. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5556 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "inject"
Process rating: all ten parameters 60/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 60Tools and files. Uses tools (bash, web, node) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Execution cost. Instruction body is 5556 tokens
- 85Steps. 108 steps, 3 vague phrases
- 100Failures and branches. 19 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 11 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (5 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
- -32 of 7 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 324: enough signal without eating the budget
- +4Structure: 20 headings
- +3Step-by-step instructions: 108 items
- +4Has examples (11 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 70.