CC creditkarma
Access Credit Karma transaction data via MCP. Use when the user asks about their Credit Karma transactions, spending by category or merchant, account summaries, account balances, or wants to sync or query their financial data. Triggers on phrases like "sync my transactions", "what did I spend on", "show my Credit Karma data", "spending by category", "top merchants", or any request involving personal finance data from Credit Karma. Requires creditkarma-mcp installed and the creditkarma server registered (see Setup below).
Access Credit Karma transaction data via MCP.
As a process C 59/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
What is at stake
The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.
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
- Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
- 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
-
high Exfiltration
intent-browser-credential-storeSKILL.md:63Accesses a browser credential / cookie store**1. ContextMint Bridge extension (easiest — no env vars):** Install [ContextMint Bridge](https://github.com/nullnet-app/contextmint-bridge/releases) (Chrome: load the chrome zip unpacked; Safari: shi
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 59/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 30Running it twice. 1 mutating operations with no state check
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 21 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1834 tokens
- 100Progress reporting. Reports progress
- high The skill tells the model to perform an irreversible action with no human approval
- low The response is described with custom markup (3 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
- +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
- +5Description quotes 5 example trigger phrases
- +3Description length 526: enough signal without eating the budget
- +4Structure: 13 headings
- +3Step-by-step instructions: 21 items
- +4Has examples (7 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.