What it does
This skill supports security reviews of applications or systems, including those built quickly with AI coding agents. It produces a STRIDE threat model, a LINDDUN privacy threat model, and a dependency exposure screen checked against live CVE, CISA-KEV and EPSS data. It also provides a selected, non-exhaustive screen of which EU security obligations (GDPR, NIS2, Cyber Resilience Act, AI Act) may apply and which need determination. The workflows are orchestrated through the Ansvar Gateway MCP connector, whose server enforces them.
It suits cases where a review needs regulatory grounding rather than only a technical checklist. Every regulatory statement is grounded in officially published text fetched at the time of the answer, with scope, role and application-date limits stated. The output is not a compliance verdict. The skill does not simulate workflows and does not answer legal questions from model memory.
Running it requires access to the Ansvar Gateway MCP connector, since the threat-modeling workflows run on that server. The skill is licensed under CC-BY-4.0.
Limitations and requirements
Requires the Ansvar Gateway MCP connector, whose server enforces the threat-modeling workflows. The EU obligation screen is selective and non-exhaustive, and it is not a compliance verdict. Legal questions are not answered from model memory, and regulatory statements carry scope, role and application-date limits.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- AI Templates (aitmpl) first seen 13 Nov 2026 · last seen 17 Nov 2026 · its page on the source · figures reported by the source: aitmpl downloads 9
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 ti
v1.2As shown on www.aitmpl.com when we last read it