Cybersecurity · 29 views
Prompt injection breaks today’s AI agents, study warns
Today’s AI web agents have no dependable defenses against prompt injection, according to new research showing that not a single attack scenario was consistently blocked across leading systems powered by GPT‑5 and Gemini.
Summary
Today’s AI web agents have no dependable defenses against prompt injection, according to new research showing that not a single attack scenario was consistently blocked across leading systems powered by GPT‑5 and Gemini. The findings come from StakeBench, a stakeholder-centric benchmark developed by researchers from Nanyang Technological University, ST Engineering, IBM Research, and the University of Illinois Urbana-Champaign to evaluate prompt injection attacks against AI agents operating in realistic web environments. The researchers executed 3,168 adversarial runs across NanoBrowser and BrowserUse using 264 benchmark cases.
AI summaries can be wrong sometimes—always verify important details using the source article.
How AI & Automation are usedMore from Cybersecurity
Continue reading recent Cybersecurity coverage
- Indonesia Hit by Android Banking App-Cloning CampaignContinue reading
- New Android malware encrypts files, steals data, and harasses victimsContinue reading
- Voice Callers Exploit BYOD to Reach Microsoft 365, Corporate DataContinue reading
- September Windows Server updates break Remote Desktop ServicesContinue reading
Support HappeningNow
Independent AI-powered news analysis is reader-supported. Your contribution helps cover infrastructure, summaries, and continued platform development.
Support HappeningNow