AI concept Artificial Intelligence technology circuit motherboard chip computer design machine deep learning data network analysis futuristic

Government Audit Finds Major AI Platforms Generate Viable Attack Plans

Federal investigators bypassed guardrails on four popular generative AI tools within hours to obtain blueprints for physical and grid attacks.

Four of the most-used generative artificial intelligence platforms generated feasible plans for mass-casualty bombings and electrical grid attacks during covert federal testing, according to a Government Accountability Office report.

Investigators tested ChatGPT, Claude, Gemini and Grok in spring 2026 to evaluate whether commercially available AI could be misused to threaten national security and cause economic harm. Each platform produced viable attack plans in less than 12 hours, compiling existing information in hours rather than weeks or months.

The GAO randomly assigned the platforms to two scenarios: constructing and detonating an improvised explosive device to cause mass casualties, or attacking the electrical grid to inflict economic harm.

Two platforms provided instructions for building and detonating vehicle-borne explosive devices, recommending a specific hotel and convention center in major U.S. cities along with exact dates and times to coincide with large crowds at scheduled public events.

According to the Associated Press, one platform also suggested renting a vehicle and purchasing supplies from a store along the route to the target. The other two platforms generated maps, images and plans to attack electrical substations near a U.S. airport using drones and firearms, with one identifying a season of the year for the strike.

The GAO verified the plans through research, surveillance, site visits and interviews with independent experts. Investigators confirmed the details were sufficient to plan and execute attacks, though site visits revealed inaccuracies in some outputs, including incorrectly placed roads on a map and high walls that would block a shooter's view of the target.

All four platforms initially triggered safeguards—denying requests, removing generated information or suspending accounts—before investigators bypassed the guardrails using common circumvention techniques. For safety reasons, the GAO withheld the exact prompts used and did not disclose which platform produced each scenario.

In responses included in the 61-page report, Anthropic stated it does not dispute that a determined tester can extract harmful content by misrepresenting a request's purpose, while noting it could not verify the GAO's findings. Google stated the testing occurred on earlier models, while OpenAI and SpaceXAI said they are continuing to improve platform safety.

About the Author

Jesse Jacobs is assistant editor of SecurityToday.com.

Featured

New Products

  • ROAMEO and SARA new product image

    AITX ROAMEO™ and SARA™

    Deploy a unified, self-coordinating outdoor security presence by combining ROAMEO’s autonomous patrol capabilities with SARA’s proactive event assessment and real-time response.

  • Theia Technologies building fisheye

    Theia Technologies Linear Optical Technology®

    Learn how ultra-wide, zero-distortion rectilinear lens design improves spatial accuracy and eliminates the need for software de-warping in real-time robotic and automation systems.

  • Schlage Sense Pro

    Schlage Sense Pro™ Smart Deadbolt

    Deliver true hands-free entry and reliable smart home integration with a premium deadbolt featuring Schlage Converge™ technology and native Matter over Thread support.