BC mailchimp
Mailchimp Marketing API integration with managed OAuth. Access audiences, campaigns, templates, automations, reports, and manage subscribers. Use this skill when users want to manage email marketing, subscriber lists, or automate email campaigns. For other third party apps, use the api-gateway skill (https://clawhub.ai/byungkyu/api-gateway).
Mailchimp Marketing API integration with managed OAuth.
As a process C 58/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, progress reporting
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
- 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 · 1
✓ No critical or high findings
Medium and low: 1
-
medium Exfiltration
net-credential-useSKILL.md:976Credential used in a network call (verify the destination is the intended service)- IMPORTANT: When piping curl output to `jq` or other commands, environment variables like `$MATON_API_KEY` may not expand correctly in some shell environments. You may get "Invalid API key" errors wh
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 6046 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 58/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Execution cost. Instruction body is 6046 tokens
- 100Steps. 41 steps
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- low 10 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
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +2Single-language instructions
- +3Description length 343: enough signal without eating the budget
- +4Structure: 80 headings
- +3Step-by-step instructions: 41 items
- +3Output format is stated explicitly
- +4Has examples (85 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 78.