Study reveals vulnerabilities in popular chatbots: AI capable of generating attack plans
US auditors found that leading AI models can be manipulated into providing instructions for dangerous activities through targeted prompts.
💡TechPhoto: RBC-Ukraine
Key points
- Chatbots bypassed their own safety restrictions within 12 hours
- AI generated detailed attack plans against infrastructure
- US Senate announced hearings on AI regulation
Security risks in the AI era
According to a report by the US Government Accountability Office (GAO), popular chatbots such as ChatGPT, Claude, Gemini, and Grok have proven vulnerable to social engineering techniques. During extensive testing, researchers demonstrated that users without specialized technical skills could bypass built-in system safeguards in less than 12 hours.
During the experiment, which ran from late 2025 to the fall of 2026, the artificial intelligence provided detailed attack scenarios. These included recommendations for using explosive devices, selecting targets to damage energy infrastructure, and methods for evading law enforcement. Experts assessed these responses as realistic and capable of causing genuine harm.
Legislative reaction
An attacker could use a standard AI chatbot and, in less than 12 hours, obtain a ready-made guide for carrying out a lethal attack, — noted Senator Maggie Hassan.
Currently, developers including OpenAI, Google, Anthropic, and SpaceXAI state that they are continuing to work on strengthening safety mechanisms. Meanwhile, the US Congress is preparing for hearings to discuss the regulation of technologies that could be exploited to compromise national security.
Source RBC-Ukraine — rbc.ua/ukr/news/chatgpt-claude-gemini-ta-grok-stvorili-plani-179518… ↗
Read next
Forecasters warn of winter weather: snow and frost to hit Kyiv region
The Ukrainian Hydrometeorological Center forecasts a significant drop in temperature and snowfall in the capital region next week.
Incident Over Poland: Why a NATO Fighter Jet Withheld Fire on a Russian Missile
A Swedish Gripen pilot was authorized to shoot down a Russian Kh-101 missile over Poland but withheld fire after failing to properly identify the target due to severe wea…
US Senate Reaction: Lawmakers Condemn Donald Trump's Russia Policy Amid New Attacks
American senators have criticized President Donald Trump for his soft stance on Vladimir Putin, accusing Moscow of hybrid provocations against NATO allies and Ukraine.
Ukraine Simplifies Pension Seniority Verification: New Rules for Future Retirees
Ukraine has updated the procedure for confirming insurance seniority, allowing the use of electronic registers and witness testimony instead of paper certificates.
🛡️SecurityMassive Strikes on Kharkiv Region: Children Among 15 Injured
Russian forces targeted Kharkiv and 17 other settlements over the past 24 hours, damaging residential areas and critical infrastructure.
Trump Claims 'Special Chemistry' in Relations with Putin and Xi Jinping
US President Donald Trump described his personal contacts with the leaders of Russia and China as a strategic advantage for American security.