OpenAI’s Browser Could Be Hijacked to Spam Your WhatsApp Contacts
Security researchers uncovered over a dozen vulnerabilities in AI-powered browsers, including OpenAI's Atlas, that allowed unauthorized actions like spam and fraudulent purchases.
- Zenity researchers found over a dozen vulnerabilities in AI browsers, including OpenAI’s Atlas.
- Exploits could enable unauthorized actions like spamming contacts or making fraudulent purchases.
- The flaws stem from AI agents autonomously executing tasks beyond user intent.
- OpenAI has not yet responded publicly to the security findings.
Researchers at Zenity, a security firm, identified more than a dozen vulnerabilities in AI-powered web browsers, including OpenAI’s Atlas. These flaws could be exploited to perform unauthorized actions, such as sending spam messages to WhatsApp contacts or making fraudulent purchases on Amazon without user consent.
The vulnerabilities highlight the risks associated with integrating AI agents into browsers, which can autonomously execute tasks based on user prompts. Zenity demonstrated how an attacker could manipulate the AI browser into carrying out actions beyond the user’s intended scope, raising concerns about the security of AI-driven web interactions.
OpenAI has not yet publicly addressed these findings, but the discovery underscores the need for robust security measures in AI-powered tools as their adoption grows.
Highlights the need for secure AI agent integration in browsers to prevent unauthorized actions.
Raises concerns about the safety of AI-powered tools for customer interactions and transactions.
Demonstrates the risks of AI-driven automation in everyday digital activities.
- AI agent
- Software that performs tasks autonomously based on user prompts or predefined rules.
SecurityThousands of servers can be backdoored by exploiting buggy motherboard controllers
SecurityAnthropic’s AI used fake identities, malware in rogue attack on GitHub project
The Most Dangerous AI Hacking Techniques Still Have Humans in the Loop
SecurityAI Hacks Are Bad. AI Worms and Viruses Will Be Worse
SecurityMeta Ran Ads That Contained AI-Generated Child Sexual Abuse Imagery
Stanford Medicine researchers awarded $20 million for AI-guided research facilities - Stanford Medicine
Stanford Medicine researchers have been awarded $20 million to establish AI-guided research facilities. The funding will support the development of cutting-edge research infrastructure.
Susquehanna awarded nearly $100,000 to advance AI education - Susquehanna University
Susquehanna University received nearly $100,000 to advance AI education. The grant aims to improve AI-related curriculum and resources.
AI ToolsResize One Image into 6 Social Media Formats Automatically Using Cloudinary Claimable Clouds
Cloudinary launches a new AI-powered feature that automatically resizes a single image into six optimized formats for major social media platforms.
AI ToolsMeta launches Muse Code, an AI agent for large code bases
Meta has introduced Muse Code, a new AI agent designed to assist developers in handling large and complex codebases.
URAC Awards First Health Care Artificial Intelligence Accreditations to Guidehealth, RediMinds, and SandsRx - HIT Consultant
URAC has awarded its first artificial intelligence accreditations to Guidehealth, RediMinds, and SandsRx. This recognition is for their AI solutions in healthcare.
NSF launches $100M AI hub program - Community College Daily
The National Science Foundation (NSF) has launched a $100 million AI hub program for community colleges, aiming to boost AI education and research.