Prompt injection breaks today’s AI agents, study warns | HappeningNow.news

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.

Source Summary Published June 12, 2026 Brief Under 1 min brief
Story intelligence
Coverage Single outlet Single-outlet story
Views 29 Community interest
Brief read Under 1 min brief 85 words

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.

Read original at Csoonline

More from Cybersecurity

Continue reading recent Cybersecurity coverage

Support HappeningNow

Independent AI-powered news analysis is reader-supported. Your contribution helps cover infrastructure, summaries, and continued platform development.

Support HappeningNow

Report an issue with this page