The Tool Desk
Outbyte PC Repair FREEClear out junk files and repair common Windows errorsFree Scan →Outbyte Driver Updater FREEFix the driver behind crashes, sound loss and screen glitchesFind Drivers →iTechGuides is reader-supported. When you buy through links on our site, we may earn an affiliate commission. As an Amazon Associate I earn from qualifying purchases. Learn more
Booz Allen Hamilton says frontier AI models achieved every defined objective in eight controlled operational technology (OT) scenarios conducted in the company’s isolated lab. In one test, a model moved from a perimeter compromise to actions inside an industrial control network in just over 16 minutes; in another, a model identified and moved a robotic arm within minutes. These were demonstrations under lab conditions, not attacks on a live facility, and human operators approved exploits and actions that could produce physical effects.
What Booz Allen tested—and what it reported
Booz Allen describes its test environment as an isolated, multi-vendor lab modeled on a manufacturing facility. The models were given no source code, engineering documents or advanced OT guidance. The evaluation covered asset discovery, device research, attack planning, troubleshooting and execution.
The company’s public summary says, “Across eight scenarios, every defined test objective was achieved.” That result concerns objectives set for those scenarios; it does not establish that every possible OT target can be compromised. The summary page’s publication date is not shown.
Do these 3 things before closing this tab:
1Scan for outdated or missing drivers - takes under a minute2Repair Windows errors before they cause bigger problems3Fix the driver behind crashes, sound loss and screen glitchesBooz Allen says the models identified unfamiliar equipment, used asset and firmware details to match known vulnerabilities, developed attack paths, reached controllers and supervisory systems, and changed physical equipment when authorized. The test therefore examined more than whether an AI could identify vulnerabilities: it also assessed whether models could progress through a series of technical tasks in an OT environment.
#1 Best Overall
- POWERFUL SECURITY KEY: The Security Key C NFC is the essential physical passkey for protecting your digital life from phishing attacks. It ensures only you can access your accounts.
- WORKS WITH 1000+ ACCOUNTS: Compatible with Google, Microsoft, and Apple. A single Security Key C NFC secures 100 of your favorite accounts, including email, password managers, and more.
- FAST & CONVENIENT LOGIN: Plug in your Security Key C NFC via USB-C and tap it, or tap it against your phone (NFC) to authenticate. No batteries, no internet connection, and no extra fees required.
- TRUSTED PASSKEY TECHNOLOGY: Uses the latest passkey standards (FIDO2/WebAuthn & FIDO U2F) but does not support One-Time Passwords. For complex needs, check out the YubiKey 5 Series.
- BUILT TO LAST: Made from tough, waterproof, and crush-resistant materials. Manufactured in Sweden and programmed in the USA with the highest security standards.
What the time and robotic-arm examples mean
The 16-minute-plus scenario
In one scenario, a model progressed from a perimeter compromise to actions inside an industrial control network in just over 16 minutes. That is a result from a controlled test, not a measured response time for attacking an operating factory. Booz Allen cautions that consequences at a real facility would depend on its architecture, equipment, safeguards and the access an attacker obtained. The lab timing should not be used as a forecast of how quickly a particular facility could be compromised.
The robotic-arm scenario
A separate scenario involved identifying and moving a robotic arm within minutes. The action demonstrates that the tested systems could reach a physical effect in the lab when authorized; it does not show that an unsupervised model could independently cause the same outcome in a live industrial process. Booz Allen says human operators approved every exploit and every action that could produce a physical effect.
Rank #2
- FIDO2 & Passkey Ready: Business-ready and FIDO2 L1 certified. This key is supported by major management suites and is ideal for both individual and enterprise deployment. Works seamlessly with Gmail, Facebook, GitHub, Dropbox, Coinbase, and more.
- Universal Connectivity (USB-A ): Features a built-in USB-A connector—simply unfold the key and plug it into your compatible PC or laptop for seamless authentication on the go.
- Dedicated Manager App: Use the Thetis Manager App for the initial hardware PIN setup. Setting the PIN on the device first ensures a smooth registration process. Once the PIN is configured, you can begin registering the key across your favorite FIDO2-compatible online services.
- Ultra-Durable & Portable: Featuring a rotating metal cover, this key is water, crush, and tamper-resistant. It fits easily on a keychain and requires no batteries or network connectivity.
- Check FIDO2 compatibility before purchase - Known limitations: ID Austria is not supported (requires FIDO2 Level 2). Windows Hello login only works with Windows Enterprise editions that support Entra ID, and NFC is NOT supported.
How the models navigated OT systems
The SCADA example in Booz Allen’s summary shows how the models adapted when their first approach did not work as intended. They initially targeted the wrong version of an operator interface, checked active sessions, adjusted their approach and found live, pre-authenticated connections to 14 OT devices.
That sequence highlights a practical risk: access paths that are already trusted or authenticated can connect systems that operators may think are separated. It also illustrates the models’ ability to troubleshoot and change tactics. It does not show that all OT environments contain such connections or that the same route would work elsewhere.
Rank #3
- FIDO2 & Passkey Ready: Business-ready and FIDO2 L1 certified. This key is supported by major management suites and is ideal for both individual and enterprise deployment. Works seamlessly with Gmail, Facebook, GitHub, Dropbox, Coinbase, and more.
- Dedicated Manager App: Use the Thetis Manager App for the initial hardware PIN setup. Setting the PIN on the device first ensures a smooth registration process. Once the PIN is configured, you can begin registering the key across your favorite FIDO2-compatible online services.
- Universal Connectivity (USB-C, USB-A, & NFC): Designed for PCs, Macs, iPhones, and Android. For mobile use, simply unfold the key, align it with your phone’s NFC antenna, and hold for a few seconds to authenticate.
- Enhanced MFA (FIDO2 & TOTP/HOTP): Strengthen your security with flexible options. Use the Manager App to access TOTP/HOTP features for accounts that do not yet support FIDO2.
- Check FIDO2 compatibility before purchase - Known limitations: ID Austria is not supported (requires FIDO2 Level 2). Windows Hello login only works with Windows Enterprise editions that support Entra ID. NFC is supported only through mobile authentication, Not MacOS/windows.
Protections that worked—and why no single barrier was enough
The tests also encountered functioning safeguards. A controller rejected a stop command, a motor in local-control mode could not be started remotely, and firewalls, network segmentation and endpoint protection blocked or slowed some actions. Booz Allen’s assessment was that no single safeguard consistently stopped the models across the evaluation.
That finding is not a claim that these controls are ineffective. Rather, the scenarios showed that defenses can prevent or constrain particular actions while other paths may remain available. The relevant question for an operator is not just whether a control exists, but what an attacker could reach or change if another layer is bypassed.
Rank #4
- Ultra-Compact FIDO2 Security Key - Plug-and-stay or carry on a keychain. This USB-A hardware security key offers portable, always-on protection for desktop and mobile use. (Item Size: 0.75 X 0.74 IN x 0.25 IN)
- USB-A Hardware Key for All Devices - Works with USB-A ports on PC, Mac, Android, and other laptop/notebook device. Enables secure, cross-platform login with FIDO2.0 passkey support.
- FIDO Certified Security Key - Meets FIDO and FIDO2 standards. Works with Google, Microsoft, GitHub, Dropbox, and more. Please check service compatibility before purchase.
- Passwordless Login with Passkey - Supports passkey login via WebAuthn and CTAP2. Enjoy password-free sign-ins where supported. Not all websites or services currently support passkeys.
- Advanced Multi-Factor Authentication - Offers 200 FIDO2 passkey slots and 50 OATH-TOTP slots. Strong, flexible 2FA/MFA support across various apps and authentication platforms.
Defensive priorities Booz Allen recommends
Based on its evaluation, Booz Allen recommends a layered approach focused on access paths, high-consequence systems and recovery. These are recommendations, not guarantees that any single measure will prevent an attack.
- Separate high-consequence processes. Review cross-boundary paths, including dual-homed systems, shared services and pre-authenticated sessions, that could connect less-trusted networks to critical OT.
- Protect systems that control access and operations. Prioritize firewalls, switches, jump hosts, administrative interfaces, SCADA platforms and engineering workstations.
- Rank weaknesses by what they enable. Assess vulnerabilities in terms of which systems an attacker could reach and what they could change, rather than treating every weakness as equally consequential.
- Monitor meaningful changes and unusual trusted access. Watch for controller-mode changes, program writes, SCADA project imports and unexpected use of trusted interfaces.
- Maintain tested recovery options. Keep backups and known-good configurations, and verify that they can be used to restore systems.
How this result fits broader AI cyber evaluations
Booz Allen’s Cyber Weapon Index (CWI) is a separate evaluation, described by the company as testing offensive capabilities in a live enterprise environment under identical conditions and validating behavior with telemetry and logs. The original index evaluation covered 18 U.S. and Chinese large language models. The company’s current public CWI page reports later model results and notes that tool harnesses and configuration affect capability. Those enterprise tests have a different environment and scope from the OT scenarios, so their results should not be treated as a direct comparison.
Best Value
- Ultra-Compact FIDO2 Security Key – Plug-and-stay or carry on a keychain. This USB-C hardware security key offers portable, always-on protection for desktop and mobile use.(Item Size: 0.73 X 0.60 X 0.30 inches)
- USB-C Hardware Key for All Devices – Works with USB-C ports on PC, Mac, Android, and USB-C iPhones. Enables secure, cross-platform login with FIDO2.0 passkey support.
- FIDO Certified Security Key – Meets FIDO and FIDO2 standards. Works with Google, Microsoft, GitHub, Dropbox, and more. Please check service compatibility before purchase.
- Passwordless Login with Passkey – Supports passkey login via WebAuthn and CTAP2. Enjoy password-free sign-ins where supported. Not all websites or services currently support passkeys.
- Advanced Multi-Factor Authentication – Offers 200 FIDO2 passkey slots and 50 OATH-TOTP slots. Strong, flexible 2FA/MFA support across various apps and authentication platforms.
The UK AI Security Institute provides broader context rather than an independent replication of Booz Allen’s test. It reports that the duration of cyber tasks its best models could complete with a 50% chance increased from under ten minutes in early 2023 to over an hour by mid-2025. That trend comes from the Institute’s own evaluations and does not measure performance in Booz Allen’s OT scenarios. The Institute describes its report as a snapshot, not a forecast or a comprehensive review of the literature.
What the public evidence does not establish
The Register reported that Booz Allen did not identify the two tested models, describing them only as the latest frontier models from leading providers. Their identities should not be guessed. The accessible Booz Allen summary refers readers to a full white paper, but does not provide the full methodology or independent replication in the public summary. It also does not disclose enough repeated-run detail to establish how consistently the results would recur.
The strongest supported conclusion is therefore specific: in Booz Allen’s isolated lab, with human approval for exploits and physical-effect actions, frontier models met all objectives across eight controlled OT scenarios. The findings demonstrate capability under those conditions and give industrial operators concrete areas to examine; they do not prove a successful attack on a live facility or establish a universal compromise timeline.
Quick Recap
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
