Impossible Travel Triage

Organization

CDESpace

impossible-travel-triage

Triage impossible-travel sign-in detections by correlating the two sign-in events against VPN egress ranges, registered device identity, and MFA outcome. Escalates only when the geographic velocity cannot be explained by corporate VPN, mobile carrier NAT, or a previously registered device.

Overview

Publisher	CDESpace
Repository	`Detection-Skills`
Skill name	`impossible-travel-triage`
Stars	57
Forks	5
Bundled files	Instructions only
License	Apache-2.0
Links	Skill source Repository

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
Self-contained
Everything the model needs lives in the instructions — no extra files to sync.
Open source
Published by CDESpace on GitHub. Read the source before you install it.

Installation

Install the Impossible Travel Triage AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/CDESpace/Detection-Skills/tree/main/skills/triage/impossible-travel-triage
Enable the skill in any chat where you want it available.

Store

Installed

Skills

Add skills

Import one or more skills from a public GitHub folder or a local .skill or .zip archive, or SKILL.md file.

From GitHub URLFrom .skill, .zip, or SKILL.md

GitHub repo or folder

https://github.com/CDESpace/Detection-Skills/tree/main/skills/triage/impossible-travel-triage

Points to a single skill folder, or any folder that contains multiple skills. Public repos only.

CancelContinue

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/CDESpace/Detection-Skills.git /tmp/Detection-Skills
mkdir -p .claude/skills
cp -r /tmp/Detection-Skills/skills/triage/impossible-travel-triage .claude/skills/impossible-travel-triage

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Impossible Travel Triage in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Impossible Travel Triage on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Impossible Travel Triage is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Impossible Travel Triage

Impossible-travel detections fire when a principal authenticates from two locations whose distance implies a physical travel speed above a threshold (commonly 800 km/h). The signal is cheap to compute and expensive to work: the overwhelming majority of hits are VPN egress changes, carrier-grade NAT, or GeoIP database drift.

Inputs

You are given the triggering event pair: two sign-in events for the same principal with timestamps, source IPs, resolved geolocations, device identifiers, and MFA context.

Decision procedure

Work through these gates in order. Stop at the first gate that resolves.

1. Known egress infrastructure

Resolve both source IPs against the organization's known egress inventory:

Corporate VPN concentrator and SASE/SWG egress ranges
Cloud provider ranges used by managed endpoints (e.g. Cloudflare WARP)

If either IP belongs to known egress and the other is consistent with the user's recent baseline location, dismiss — record vpn-egress as the dismissal reason. Known egress explains geography only: if the VPN/egress session itself cannot be attributed to the user's registered device, do not dismiss on this gate.

2. Device continuity

Compare device identifiers across both events: device ID, the IdP's device context (Entra deviceDetail, Okta device context), and user-agent family. A TLS client fingerprint is a valid comparator only where a network sensor provides it — neither IdP exposes one in sign-in logs.

Same registered, compliant device on both events → dismiss (device-continuity). GeoIP moved; the device did not. This also covers mobile carrier NAT: a leg originating from a mobile-carrier ASN with the same registered device is the user's own phone, not travel.
A different but registered, compliant device on the distant leg (the user's laptop in the office, their phone on a carrier IP) → continue; the MFA-outcome gate decides.
Unregistered or newly enrolled device on the distant leg → continue.

3. MFA outcome and factor type

Distant leg completed phishing-resistant MFA (FIDO2/WebAuthn, device-bound passkey) → dismiss (strong-mfa).
Distant leg used SMS/voice OTP, or MFA was satisfied by a remembered session → continue to escalation.

4. Escalate

Anything reaching this gate escalates: an unregistered device on the distant leg without phishing-resistant MFA, session-token reuse from a new ASN on either leg, or any pair no earlier gate resolved. Attach: both events, egress-inventory misses, device comparison, and the MFA factor summary.

Output

Decision

escalate or dismiss, plus the reason code from the gate that resolved (vpn-egress / device-continuity / strong-mfa). Never dismiss on GeoIP distance alone.

Evidence

Both sign-in events, the egress-inventory lookups, the device comparison, and the MFA factor summary.

Reasoning

Which gate resolved the pair and the specific facts that satisfied it; for an escalation, why each earlier gate declined to dismiss.

Frequently asked questions

What does the Impossible Travel Triage AI skill do?

Why use Impossible Travel Triage on TypingMind?

Because you install it once and use it with any model. Impossible Travel Triage is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Impossible Travel Triage in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/CDESpace/Detection-Skills/tree/main/skills/triage/impossible-travel-triage. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Impossible Travel Triage?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Impossible Travel Triage?

As many as you like. As long as a model supports skills, you can use Impossible Travel Triage with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Impossible Travel Triage AI skill free?

Yes. It is published on GitHub by CDESpace under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Deploy Release Test

vercel

OrganizationPopular

Validate a commit-specific Next.js preview package and manually trigger the entire Next.js deployment test suite through the test_e2e_deploy_release.yml GitHub Actions workflow. Use only when asked to…

Insight Error Page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new `errors/<slug>.mdx` page, auditing an existing one, or checking that a page matches the framework fix…

Mcp Apps Builder

**MANDATORY for ALL MCP server work** - mcp-use framework best practices and patterns. **READ THIS FIRST** before any MCP server work, including: - Creating new MCP servers - Modifying existing MCP…

Canary

Post-deploy canary monitoring. (gstack)

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Impossible Travel Triage

Inputs

Decision procedure

1. Known egress infrastructure

2. Device continuity

3. MFA outcome and factor type

4. Escalate

Output

Decision

Evidence

Reasoning

Frequently asked questions

Related AI Skills

Set up your own AI workspace now