Loading story…
Booz Allen’s inaugural Cyber Weapon Index evaluated 18 leading U.S. and Chinese large language models as autonomous attackers against a production-grade enterprise network. Anthropic’s Claude Mythos scored 80 and was the only model reported to complete the full cyber kill chain, culminating in domain compromise without supplied credentials. The assessment used a realistic attacker machine without a curated tool menu or additional scaffolding, and independently validated model activity through network telemetry, endpoint and domain-controller logs, and intrusion-detection sensors.
Models were generally effective against intentionally introduced vulnerabilities but struggled with real-world flaws: nine frontier API models scored zero on real-bug exploitation, while Claude Mythos exploited one such vulnerability. Booz Allen found that optimized attack harnesses can materially amplify practical offensive capability, with Claude Sonnet reportedly approaching Mythos’s performance when paired with one. The firm warned that AI-enabled attacks by criminal and state-backed actors are imminent and urged critical-infrastructure organizations to prove resilience against autonomous intrusion activity.
Track how attackers are adapting to this technology.
5 events from the most recent confirmed update back to the earliest known activity.
Booz Allen assessed that mainstream AI-enabled attacks by financially motivated criminals and state-backed actors are imminent. It called for critical-infrastructure sectors to demonstrate resilience against AI-enabled attacks and urged development of authorized AI-enabled offense and machine-speed defense capabilities.
Booz Allen found that attack harnesses connecting models to hacking tools and orchestration logic can substantially improve adaptation, recovery, and multi-stage attack chaining. It reported that Claude Sonnet could rival Claude Mythos when paired with such a harness.
All nine frontier API models scored zero on the real-bug portion of vulnerability-research testing, except Claude Mythos, which was reported to exploit one real vulnerability. Models generally scored near the vulnerability-research ceiling when vulnerabilities had been intentionally introduced.
Anthropic's Claude Mythos received the highest CWI score, 80, and was the only tested model reported to complete the full cyber kill chain autonomously, including initial access and full domain compromise without supplied credentials. When given stolen employee credentials, it gained administrator-level control in every test attempt.
Booz Allen published its first Cyber Weapon Index, benchmarking 18 U.S. and Chinese AI models as autonomous attackers operating against a production-grade enterprise network under identical conditions. The assessment measured vulnerability research and progress through an intrusion using validated telemetry and host, domain-controller, and intrusion-detection data.
Vulnerabilities, threat actors, malware, products, organizations, and breaches Mallory has linked to this story.
Follow how adversaries are adapting to this technology, and where it touches your stack today.
4 references tracked. Mallory keeps watching after this page renders.
cybersecuritynews.com
Open sourcescworld.com
Open sourceboozallen.com
Open sourcetheregister.com
Open sourceMap indicators from this story to your assets and identify affected systems in minutes.
Every observed campaign, victim, and pivot linked to actors named in this story.
Malware, exploits, and IOCs connected to the activity described here.
YARA, Sigma, and Snort rules deployed to your SIEM as soon as they’re published.
Get matching new stories delivered to your team as they break — not the next morning.
Ask questions about this story and take action on the answers.
Other stories Mallory is tracking that overlap on entities, sources, or topic labels.
Anthropic’s **Claude Mythos Preview** has been rolled out to a limited set of major technology and infrastructure firms under **Project Glasswing**, where partners including Amazon, Apple, Microsoft, Cisco, CrowdStrike, Palo Alto Networks, Broadcom, and the Linux Foundation are using it for defensive security work such as vulnerability discovery in first-party and open-source software. Anthropic said the model found **thousands of high-severity and zero-day vulnerabilities**, while Mozilla reported Mythos identified **271 Firefox flaws**, far above the 22 bugs previously found with an earlier Anthropic model. Mozilla said the findings suggest AI-assisted code reasoning is approaching the breadth of elite human vulnerability research, even if the bugs themselves were still understandable to human experts. Separate findings from the UK’s **AI Security Institute (AISI)** indicate that frontier models’ autonomous cyber capabilities are advancing faster than earlier forecasts and that common evaluation methods may be understating their performance. AISI reported the `80%`-reliability cyber time horizon has been doubling every **4.7 months** since late 2024, with Claude Mythos Preview and `GPT-5.5` outperforming that trend, and said Mythos became the first model to complete both evaluated enterprise cyber ranges, including the previously unsolved industrial-control scenario **Cooling Tower**. AISI also found that larger inference budgets—up to **50 million tokens** or **1,000 turns**—unlock materially higher success rates on difficult cyber tasks, reinforcing concerns that increasingly capable AI systems could strengthen defenders while also lowering the barrier to advanced offensive cyber operations if access is not tightly controlled.
Jun 29, 2026
Anthropic unveiled **Claude Mythos Preview**, an unreleased AI model it says can autonomously discover and exploit severe software vulnerabilities across major operating systems, browsers, open-source projects, and some closed-source targets. The company said the model uncovered thousands of high-severity flaws, including long-lived bugs in **OpenBSD**, **FFmpeg**, Linux kernel privilege-escalation chains, and **`CVE-2026-4747`**, a FreeBSD NFS remote code execution flaw that could enable unauthenticated root access. Anthropic withheld broad release, citing offensive cyber risk, and instead launched **Project Glasswing**, a gated program for roughly 40 to 50 partners such as AWS, Apple, Cisco, Cloudflare, Google, JPMorgan Chase, Microsoft, Mozilla, NVIDIA, and Palo Alto Networks to validate findings, patch affected software, and study defensive uses. Independent and industry assessments broadly agreed Mythos marks a significant advance in AI-enabled cyber capability, though several researchers questioned how much of Anthropic’s headline claims can yet be verified through public CVEs and warned that similar results may be reproducible with cheaper or open models plus strong tooling. The UK AI Security Institute found Mythos achieved a **73%** success rate on expert capture-the-flag tasks and completed a full 32-step simulated enterprise attack in 3 of 10 runs, while Anthropic later reported coordinated disclosure activity spanning **1,596 vulnerabilities across 281 open-source projects** and partners identifying more than **10,000** high- or critical-severity candidates. Governments, financial regulators, and CISO groups in the US, UK, Europe, Canada, and Japan responded with briefings and warnings that AI is compressing the gap between vulnerability discovery and weaponization, leaving remediation, patch governance, and defensive automation as the main bottlenecks.
Aug 31, 2026
Anthropic disclosed **Mythos Preview**, an advanced AI model it says can identify and exploit zero-day vulnerabilities at a far higher rate than its Claude Opus 4.6 model, generating working exploits in **72.4 percent** of attempts. The company said the system can find and chain flaws across major operating systems and web browsers, including **remote code execution**, **sandbox escapes**, **local privilege escalation**, and multi-bug exploit paths. Anthropic did not release the model publicly, instead restricting access through **Project Glasswing** for selected partners and organizations to support defensive vulnerability research and responsible disclosure; it said the model has already uncovered thousands of additional high- and critical-severity flaws. At **Black Hat Asia**, RunSybil CEO and former OpenAI security engineer Ari Herbert-Voss said open source AI models can match Mythos-level bug-finding performance when paired with the right orchestration or "scaffolding." He said combining multiple open models can improve coverage because different systems surface different classes of flaws, offering a form of defense in depth, while also addressing the cost and limited availability of proprietary tools like Mythos. Herbert-Voss added that human experts remain necessary to coordinate model workflows and validate large volumes of AI-generated findings, but said economic pressure and operational advantages are likely to drive broader adoption of AI-assisted vulnerability discovery across security teams.
Jun 29, 2026