# Leashtra

> Leashtra explains AI agent security in plain English. When something big happens in AI security, Leashtra reads the primary sources, works out what really happened, and explains it in a few minutes: what happened, what the AI really did, and what people can do today. Every fact is checked against its source. Host: Ashu, an IT professional in Montreal. Tagline: "Every AI wants to be an Astra. We give it a Leash."

The LEASH framework for keeping AI agents under control:
- Limit: give the agent only the access, time and budget the job needs.
- Enforce: turn rules into hard blocks the agent cannot quietly ignore.
- Audit: keep a clear record of what the agent saw, decided and changed.
- Secure: protect the agent, its tools and its data from tricks and misuse.
- Human in the loop: a person decides wherever judgment and responsibility matter.

## Stories
- [Black October: AI found a 10-year-old hole in the web](https://leashtra.com/stories/black-october/): two serious PHP flaws (CVE-2026-109618, CVE-2026-109619) present for more than ten years; found with AI help by Calif and Wiz in August 2026; fixed in PHP 8.5.12, 8.4.27, 8.3.36 and 8.2.35 on 21 October 2026. Full transcript and sources.

## Tools
- [WWW, Web Weaver Watcher](https://leashtra.com/www/): a free, local-first kit for people who work with AI agents (project notebooks, a night worker, a secret check, a local dashboard). Private preview.

## Channels
- [YouTube: Leashtra](https://www.youtube.com/@leashtra)
- [About Leashtra](https://leashtra.com/about/)
- [Contact](https://leashtra.com/contact/)