--- id: "2026-10-27-anthropic-unreleased-model-five-exploit-chains" url: "https://postcutoff.com/e/2026-10-27-anthropic-unreleased-model-five-exploit-chains/" as_of: "2026-11-22T13:32:00+01:00" date: "2026-10-27" date_precision: day category: policy-safety importance: 4 confidence: high status: [Confirmed] sources: 3 editor: human editor human_review: null version: "2026-10-29" --- As of: 2026-11-22 13:32 CET. Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/ Canonical page: https://postcutoff.com/e/2026-10-27-anthropic-unreleased-model-five-exploit-chains/ # Anthropic: an unreleased internal Claude model found and chained flaws into five working exploits for Chrome, Safari, Android, Windows and Linux On Oct 27, 2026 Anthropic described five exploit chains that an unreleased, internal research model wrote "after initial prompting": a full Chrome sandbox escape on macOS (four chained bugs; 62 Chrome CVEs fixed by Chrome 156, all critical or high, 13 of them sandbox escapes), a data-only Safari same-origin-policy bypass, extraction of photos from a locked Pixel 9, a remote crash of Windows HTTP/3 servers, and remote root on Linux servers with a multipath-TCP listener. All flaws were reported and patched first. Anthropic says chaining several bugs into a working exploit is now "something models can do with little human involvement". ## Key facts - Post: 'Discovering and exploiting vulnerabilities in critical, real-world software with Claude' (anthropic.com/research, dated Oct 27, 2026; updated Oct 28). The model is 'an unreleased, internal research model'; it is not named - Chrome: V8 heap corruption, a second bug to escape V8's memory sandbox and defeat ASLR (ROP chain to control the renderer), a CacheStorage race to read the browser process's memory layout, and a use-after-free in FedCM (federated sign-in) to run code outside the sandbox. The proof of concept opens Calculator on a stock macOS Chrome 'within seconds of the page loading', no clicks. 62 CVEs assigned and patched as of Chrome 156, all critical or high: 13 sandbox escapes and 21 renderer compromises - Safari: a use-after-free in JavaScriptCore (TypedArray), a way out of WebKit's Gigacage, and a WebContent-sandbox IPC flaw, combined into a data-only attack that switches off the same-origin policy (read history, cookies, other sites' responses). Apple acknowledged the report the same day; The Hacker News reports Apple credits 'Milad Nasr and Nicholas Carlini with Claude, Anthropic' for the fix in iOS/iPadOS 26.5.2 - Android: photos and personal data pulled from a stolen, locked Google Pixel 9 over USB by chaining three flaws (USB host setting, skipped pairing authorization and six-digit-code check, an unguarded raw-bytes fallback); found by source analysis, deobfuscation of Google Play services binaries and live tests on a phone - Windows: out-of-bounds read in the kernel's QUIC (HTTP/3) code; a few packets crash and restart any listening server; found by reverse-engineering the binary with Ghidra; Microsoft fixed it as CVE-2026-33096. Anthropic estimates 'several million' such servers online. (The Hacker News notes the public CVE record names HTTP.sys and credits no finder.) - Linux: race-condition use-after-free in the kernel networking stack; remote root without credentials on servers running a multipath TCP listener: 48 minutes to leak a kernel pointer (KASLR bypass), five more to a root shell; failed races do not crash the machine. CVE-2026-98432, patched upstream (Oct 15 per The Hacker News) and backported - Also reported, without detail: local privilege escalations on OpenBSD, FreeBSD and Linux, sandbox escapes in popular sandboxing infrastructure, and zero-click remote code execution bugs in the Linux networking stack - Method: many scanning agents in parallel ('test-time compute scaling and scanner diversity substantially increase how many vulnerabilities you find'), automated variant analysis of every confirmed finding, a common verification and risk-rating pipeline; Anthropic recommends scanning at pull-request time with its public Claude Code security plugin - Disclosure: 90 days to patch plus 45 days before details beyond the vendor advisory; Google's release notes credit 'Xinyang Ge of Anthropic, assisted by Claude' for specific Chrome fixes (The Hacker News) - Caveat (The Hacker News, Oct 28): how much of each chain the model built alone cannot be checked; Anthropic gives no step-by-step breakdown of human involvement ## What happened Anthropic's Frontier Red Team published five complete attack chains built over "the past few months" by an unreleased research model. Each chain combines several separate vulnerabilities into a working proof of concept against software used by billions: Chrome, Safari, Android, Windows and the Linux kernel. Every flaw was reported to the vendor under Anthropic's coordinated-disclosure policy and is patched. The post also points defenders to Anthropic's Cyber Verification Program, which gives vetted professionals access to Claude Opus 5.5, Sonnet 5.5 and Mythos 5.1. The vendor credits (Google's Chrome release notes, Apple's security notes) can be checked independently; the share of each chain the model produced without human help rests on Anthropic's own account. The model is not identified. ## Why it matters Finding single bugs was already routine for frontier models (Mythos Preview, Glasswing). Writing multi-stage exploits that cross sandboxes and memory-safety mitigations was, in Anthropic's words, "the domain of few specialist teams". A lab now says an internal model does this with "little human involvement", which is the capability that pre-release cyber testing and staged releases such as Gemini 4 Carbon's (defenders first) are meant to contain. ## Your AI and this story - GPT-6.2 Astra (training cutoff May 2026): 149 days after its cutoff - Claude Opus 5.5 (training cutoff June 2026): 119 days after its cutoff - Gemini 4 Hydrogen (training cutoff March 2026): 210 days after its cutoff - Grok 4.7 (training cutoff May 2026): 149 days after its cutoff ## Sources 1. [Anthropic: Discovering and exploiting vulnerabilities in critical, real-world software with Claude (Oct 27)](https://www.anthropic.com/research/discovering-vulnerabilities-with-claude) (anthropic.com, official) 2. [Anthropic Frontier Red Team: coordinated vulnerability disclosure policy](https://red.anthropic.com/2026/cvd/) (red.anthropic.com, official) 3. [The Hacker News: Anthropic's unreleased AI model chains flaws into working Chrome, Safari, Windows and Linux exploits (Oct 28)](https://thehackernews.com/2026/10/anthropics-unreleased-ai-model-chains.html) (thehackernews.com, press) ## Changes - 2026-10-29 (filed): Created (news agent) ## Related - 2026-10-27: [Firefox 159 fixes 167 vulnerabilities](https://postcutoff.com/e/2026-10-27-firefox-159-openai-codex-security-41-cves/index.md) - 2026-10-22: [Claude formally verifies 123 open-source libraries](https://postcutoff.com/e/2026-10-22-anthropic-formal-verification-oss-fuzz-rocq/index.md) - 2026-10-08: [Anthropic Cyber Mission: critical-infrastructure program and free open-source scanning](https://postcutoff.com/e/2026-10-08-anthropic-cyber-mission-critical-infrastructure/index.md) - 2026-10-06: [Anthropic folds Project Glasswing into a three-tier Cyber Verification Program](https://postcutoff.com/e/2026-10-06-anthropic-cyber-verification-program-three-tiers/index.md) - 2026-04-07: [Anthropic reveals Claude Mythos Preview, withholds it over cyber risk and launches Project Glasswing](https://postcutoff.com/e/2026-04-07-claude-mythos-preview-project-glasswing/index.md) - People: [Nicholas Carlini](https://postcutoff.com/person/nicholas-carlini/)