# Anthropic says internal AI model built working exploit chains

_Published Wednesday, October 28, 2026 at 5:06 AM EDT · AI, Security · Latest · Tier 2 — Notable_

![Anthropic says internal AI model built working exploit chains — Primary](https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgSMl2C6S6mb-smamI35fLYotcPaercI_2PIgtuF78Q7PtQcFvFUKXkModTW4nRCh6FC7Xht2BltSGImRS2QNR4Lnc22S7UBU9V_0UDcZi2iDNXSlCJDqD4ApmJPqA_boFokj_9dTWKdzhjIgNt_Y47zumx_c5vrcJn5Vd-Xaowafv4HGCzCcqgDV4GGpo/s1700-nu-rw-lo-l85-e365/hacker-chain.jpg)

Anthropic says an unreleased internal AI model found security flaws and combined them into working proof-of-concept exploits across browsers and operating systems. The company described five chains built in laboratory tests after prompting; all the flaws have been patched, and the exploits were not observed in real attacks.

One Chrome demonstration opened Calculator on a stock Mac after a page loaded, without further clicks. A Linux chain obtained a root shell over the network but required a server running a multipath TCP listener.

Apple and Google credit Anthropic and Claude for specific fixes. Those acknowledgments do not establish how independently the model worked: Anthropic has not broken down human involvement at each step.

## Sources

- [The Hacker News](https://thehackernews.com/2026/10/anthropics-unreleased-ai-model-chains.html)

---
Canonical: https://techandbusiness.org/newswire/mpNgE-A9sg0vA0k5cn6WDQ
Published: 2026-10-28T09:06:01.368Z
Story chronology: 2026-10-28T08:15:07.000Z
Retrieved: 2026-10-28T11:28:25.779Z
Publisher: Tech & Business (techandbusiness.org)