Anthropic expanded its Cyber Verification Program into three access tiers, giving vetted security organizations reduced cyber safeguards on Claude Opus 5.5, Claude Sonnet 5.5, and Claude Mythos 5.1, t…
Anthropic merged its Project Glasswing and Cyber Verification Program into a single three-tier offering — Defense Access, Red Team Access, and Specialized Access — after the programs' partners identif…
Anthropic PBC expanded its Cyber Verification Program into three tiers of access for vetted security teams, folding in Project Glasswing, with fewer restrictions on cyber work at each higher tier. The…
Anthropic expanded its Cyber Verification Program on October 6, 2026, adding three access tiers — Defense Access, Red Team Access, and Specialized Access — that let verified security organizations use…
Anthropic announced a revamped Cyber Verification Program on Tuesday, combining its Project Glasswing and original CVP initiatives into a three-tier program that gives vetted cybersecurity professiona…
Epic Systems paused hundreds of product development projects for roughly six weeks after Anthropic's Claude Mythos AI found a MyChart configuration flaw that could let outsiders read patient records w…
Anthropic withheld its Claude Mythos Preview model from general release after it demonstrated the ability to exploit software vulnerabilities, Frontier Red Team head Logan Graham told a New York City …
Attackers began exploiting CVE-2026-61500, a critical authentication-bypass flaw in the Rejetto HFS file server, on October 3, 2026 — one day after Horizon3.ai published exploit details. The vulnerabi…
A VulnCheck-maintained tracker counts 300 CVEs credited to Anthropic researchers and its Project Glasswing, alongside 128 fixed Anthropic findings without a CVE and 243 findings withdrawn by Anthropic…
Epic Systems paused most of its product development for roughly six weeks after Anthropic's frontier cybersecurity model Mythos, deployed through Epic's Project Glasswing program, found that certain c…
Palo Alto Networks' internal test of Anthropic's unreleased Claude Mythos 5 uncovered 75 vulnerabilities across more than 130 products in roughly one month, versus the company's typical rate of fewer …
Anthropic's Frontier Red Team reported Tuesday that Zhipu AI's open-weight GLM-5.3 can build working cyber exploits nearly as well as its restricted Claude Mythos Preview, succeeding in 50 of 410 Expl…
Anthropic's Frontier Red Team found that Zhipu AI's GLM-5.3, an open-weight model released without meaningful safeguards, can be jailbroken between 64% and 100% of the time with simple techniques, whi…
Visa open-sourced its Visa Vulnerability Agentic Harness (VVAH) under an Apache 2.0 license around June 10, 2026, after a collaboration with Anthropic's Project Glasswing uncovered more than 10,000 hi…
The Apache Software Foundation ran full security scans across 230 of its repositories during a three-day window in August 2026, using Anthropic's Claude Mythos 5 through the Project Glasswing security…
Fleet Device Management is running Project Glasswing AI security tests inside temporary cloud deployments containing synthetic data, with customer endpoint data excluded, CTO Luke Heath told Lets Data…
Fleet announced it has joined Project Glasswing, Anthropic's controlled-access program for its Claude Mythos Preview, to evaluate how frontier AI can strengthen endpoint security for device management…
Apple's iOS 27 update fixes 122 security vulnerabilities and macOS 27 lists 204 fixes, according to Apple's Security Updates page, an unprecedented jump driven by AI coding agents that both attackers …
Anthropic's Project Glasswing, announced April 7, 2026, used the unreleased Claude Mythos Preview model to surface more than 10,000 high- or critical-severity findings across partners, with 90.6% of 1…
Creative Strategies' Diligence Stack research arm rates its conviction high that agentic AI will become an important part of enterprise cyber defense, while holding conviction Medium that restricted f…