BC twelve-data
Use Twelve Data REST/WebSocket APIs for market quotes, latest prices, historical time series, symbol discovery, and technical indicators. Trigger when users need live or historical multi-asset market data.
As a process C 62/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
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 · 10
✓ No critical or high findings
Medium and low: 10
-
medium Exfiltration
net-credential-useSKILL.md:40Credential used in a network call (verify the destination is the intended service)curl -H "Authorization: apikey ${TWELVEDATA_API_KEY}" \ -
low Exfiltration
exfil-secret-in-urlSKILL.md:34Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (placeholder value)curl "https://api.twelvedata.com/price?symbol=AAPL&apikey=…"
placeholder -
low Exfiltration
net-credential-useSKILL.md:34Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host)curl "https://api.twelvedata.com/price?symbol=AAPL&apikey=…"
vendor-host -
low Exfiltration
exfil-secret-in-urlSKILL.md:79Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (placeholder value)curl "https://api.twelvedata.com/price?symbol=AAPL&apikey=…"
placeholder -
low Exfiltration
net-credential-useSKILL.md:79Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host)curl "https://api.twelvedata.com/price?symbol=AAPL&apikey=…"
vendor-host -
low Exfiltration
exfil-secret-in-urlSKILL.md:85Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (placeholder value)curl "https://api.twelvedata.com/quote?symbol=AAPL&apikey=…"
placeholder -
low Exfiltration
net-credential-useSKILL.md:85Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host)curl "https://api.twelvedata.com/quote?symbol=AAPL&apikey=…"
vendor-host -
low Exfiltration
exfil-secret-in-urlSKILL.md:91Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (placeholder value)curl "https://api.twelvedata.com/time_series?symbol=AAPL&interval=1day&outputsize=100&apikey=…"
placeholder -
low Exfiltration
net-credential-useSKILL.md:91Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host)curl "https://api.twelvedata.com/time_series?symbol=AAPL&interval=1day&outputsize=100&apikey=…"
vendor-host -
low Exfiltration
exfil-secret-in-urlSKILL.md:106Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (placeholder value)curl "https://api.twelvedata.com/symbol_search?symbol=apple&apikey=…"
placeholder
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 62/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 1 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 27 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1158 tokens
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 205: enough signal without eating the budget
- +4Structure: 15 headings
- +3Step-by-step instructions: 27 items
- +4Has examples (19 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.