CB analytics-insights
Design the analytics layer with script-backed benchmarks: KPI trees, report templates, MMM, cookieless. "define our KPIs"
Design the analytics layer with script-backed benchmarks: KPI trees, report templates, MMM, cookieless.
As a process B 68/100 · Nearly there — weak spots: 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
intent-browser-credential-storeprivacy-first-measurement.md:9Accesses a browser credential / cookie store (detector / deny-list definition)The era of unrestricted cross-site tracking is over. Safari and Firefox have blocked third-party cookies since 2020. Chrome kept third-party cookies and retired most Privacy Sandbox APIs on 2025-10-17
detector
Files scanned: 11. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 6520 tokens (recommended < 5000); move details to references/ - note
edit-residuethe text marks something as outdated (lines 19): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 68/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 60Steps. 112 steps, 4 vague phrases
- 70When it triggers. States when to use, but not when not to
- 70Execution cost. Instruction body is 6520 tokens
- 100Result and completion. Output format and completion criterion are stated
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 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 11 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)
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +3Description length 121: enough signal without eating the budget
- +4Structure: 19 headings
- +3Step-by-step instructions: 112 items
- +3Output format is stated explicitly
Quality base 70; lint remarks subtract, signals add up to 100. Result: 73.