CB swap-planner
Plan and generate deep links for token swaps on PancakeSwap. Use when user says "swap on pancakeswap", "buy [token] with BNB", "pancakeswap swap", "I want to swap", "cross-chain swap", "bridge swap", or describes wanting to exchange tokens on PancakeSwap without writing code.
As a process B 73/100 · Nearly there — weak spots: inputs and preconditions, consistency, 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 skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
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
- 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 Broad scope
meta-broad-allowed-toolsSKILL.md:1Broad tool permissions pre-approved: Bash(curl:*)allowed-tools: Read Write Edit Glob Grep Bash(curl:*) Bash(jq:*) Bash(cast:*) Bash(xdg-open:*) Bash(open:*) WebFetch WebSearch Task(subagent_type:Explore) AskUserQuestion
-
medium Exfiltration
net-credential-useSKILL.md:233Credential used in a network call (verify the destination is the intended service)curl -s -G "https://api.dexscreener.com/latest/dex/search" --data-urlencode "q=$KEYWORD" | \
-
medium Exfiltration
net-credential-useSKILL.md:273Credential used in a network call (verify the destination is the intended service)curl -s "https://api.geckoterminal.com/api/v2/search/pools?query=…&network=…" | \
-
medium Exfiltration
net-credential-useSKILL.md:287Credential used in a network call (verify the destination is the intended service)curl -s "https://api.geckoterminal.com/api/v2/networks/${NETWORK}/tokens/${TOKEN}" | \ -
medium Exfiltration
net-credential-useSKILL.md:301Credential used in a network call (verify the destination is the intended service)curl -s "https://api.coingecko.com/api/v3/coins/${PLATFORM}/contract/${TOKEN}" | \ -
medium Exfiltration
net-credential-useSKILL.md:523Credential used in a network call (verify the destination is the intended service)curl -s "https://api.dexscreener.com/latest/dex/tokens/${TOKEN}" | \ -
low Secrets in code
secret-high-entropy-tokenSKILL.md:284High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)TOKEN="0x1f…fE6"
quoted -
low Secrets in code
secret-high-entropy-tokenSKILL.md:299High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)TOKEN="0xAc…9F1"
quoted -
low Secrets in code
secret-high-entropy-tokenSKILL.md:363High-entropy token-like string (may be an id, hash or a credential) (documentation table row)| WBNB | `0xbb…95c` | 18 |
table -
low Secrets in code
secret-high-entropy-tokenSKILL.md:364High-entropy token-like string (may be an id, hash or a credential) (documentation table row)| BUSD | `0xe9…D56` | 18 |
table -
low Secrets in code
secret-high-entropy-tokenSKILL.md:365High-entropy token-like string (may be an id, hash or a credential) (documentation table row)| USDT | `0x55…955` | 18 |
table
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 8277 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "slug" - note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 73/100
- 0Progress reporting. Says nothing while it works
- 30Inputs and preconditions. Does not say what the process needs to start
- 40Consistency. Frontmatter name (swap-planner) differs from the folder (pcs-swap-planner)
- 40Execution cost. Instruction body is 8277 tokens: crowds the task out of the window
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 53 steps
- 100Failures and branches. 12 branches, has a failure section
- 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
- low 17 top-level sections: this looks like several domains in one skill
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
- +4Description does not say when NOT to use the skill (false activations)
- +2Single-language instructions
- +5Description quotes 6 example trigger phrases
- +3Description length 276: enough signal without eating the budget
- +4Structure: 51 headings
- +3Step-by-step instructions: 53 items
- +3Output format is stated explicitly
- +4Has examples (27 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.