Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →tradecatlabs/threat-modeling
Run a structured threat-modeling session for a new feature, system, or architecture — STRIDE, attack trees, data flow diagrams, abuse cases.
Passed 17 of 23 test cases with the skill, and 14 of 23 without it.
3 fixed14 passed either way6 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 3 test cases the skill fixed. Same model, same prompt, with and without the skill.
We are starting a security review for a proposed OAuth2 single sign-on integration. A junior developer suggested using CVSS v3 scoring and threat trees. We want to structure our security review around Adam Shostack's core threat modeling framework. Can you guide us through the high-level framework?
| Checked | Without skill | With skill |
|---|---|---|
| Structures the threat modeling process around Adam Shostack's four questions: What are we working on?, What can go wrong?, What are we going to do about it?, and Did we do a good job? | Passed | Passed |
| Rejects quantitative CVSS v3 scoring in favor of qualitative likelihood and impact ratings. | Missed | Passed |
The instructions your model reads when the skill loads.
Run a structured threat-modeling session against a proposed feature, system, or architecture. This is the design-time security skill — different from audit (which inspects code that exists). Use this when there's a design doc, a feature spec, an architecture diagram — but not yet code.
When to use:
Cross-references: owasp-audit (code-level checklist that lines up with the threats this surfaces), api-audit (API-specific category mapping), iam-audit (identity decisions touch every threat model).
Adam Shostack's framing — every threat model answers these four:
The rest of this skill walks through each in order.
Produce a Data Flow Diagram (DFD) at one of three levels:
A useful DFD has:
Trust boundaries are the most useful element. If you can draw exactly one diagram that shows every trust boundary in your feature, you've already done 60% of the work.
test cases passed, vs 14 / 23 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.