AC bitpanda
Query a Bitpanda account via the Bitpanda API using a bundled bash CLI. Covers all read-only endpoints: balances, trades, transactions, asset info, and live prices. Use when the user wants to check their Bitpanda portfolio, balances, trade history, deposits, withdrawals, asset prices, or any account information from Bitpanda. Usable for mentions of Bitpanda, crypto portfolio on Bitpanda, price checks, or requests involving Bitpanda wallet/trade data. This skill is READ-ONLY — it does NOT support trading, placing orders, deposits, withdrawals, or any write operations.
As a process C 55/100 · Has gaps — weak spots: result and completion, failures and branches, consistency
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 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
- 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 · 1
✓ No critical or high findings
Medium and low: 1
-
medium Exfiltration
net-credential-usescripts/bitpanda.sh:29Credential used in a network call (verify the destination is the intended service)body=$(curl -s -w '\n%{http_code}' -H "X-Api-Key: ${BITPANDA_API_KEY}" "$url")
Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 55/100
- 0Result and completion. Does not say what the result is
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 40Consistency. Frontmatter name (bitpanda) differs from the folder (bitpanda-official)
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 9 steps
- 100Execution cost. Instruction body is 1302 tokens
- 100Running it twice. No mutating operations
- low The response is described with custom markup (8 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 573: enough signal without eating the budget
- +4Structure: 13 headings
- +3Step-by-step instructions: 9 items
- +4Has examples (11 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 90.