CB regulatory-threat-model
Use when an application or system — including one built quickly with AI coding agents — needs a security review with regulatory grounding: a STRIDE threat model, a LINDDUN privacy threat model, a dependency exposure screen against live CVE / CISA-KEV / EPSS data, or a selected, non-exhaustive screen of which EU security obligations (GDPR, NIS2, Cyber Resilience Act, AI Act) may apply and which need determination. Orchestrates the server-enforced threat-modeling workflows of the Ansvar Gateway MCP connector and grounds every regulatory statement in officially published text fetched at answer time — scope, role, and application-date limits stated, never a compliance verdict. Never simulates a workflow and never answers legal questions from model memory.
Use when an application or system — including one built quickly with AI coding agents — needs a security review with regulatory grounding: a STRIDE threat…
As a process B 68/100 · Nearly there — weak spots: result and completion, running it twice
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
-
low Risky intent
intent-offensive-securitySKILL.md:402Offensive-security / dual-use content (legitimate for authorised testing; review intended use)determination, not a penetration test, and not a code audit; a
Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 6200 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 68/100
- 0Result and completion. Does not say what the result is
- 30Running it twice. 11 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 70Execution cost. Instruction body is 6200 tokens
- 100Steps. 35 steps
- 100Inputs and preconditions. Inputs and preconditions are listed
- 100Failures and branches. 3 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low The response is described with custom markup (4 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
- +2Single-language instructions
- +3Description length 761: enough signal without eating the budget
- +4Structure: 13 headings
- +3Step-by-step instructions: 35 items
- +4Has examples (1 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.