Building Browser Agents: Architecture, Security, and Practical Solutions

Browser agents enable autonomous web interaction but face critical reliability and security challenges in production. This paper presents findings from building and operating a production browser agent. The analysis examines where current approaches fail and what prevents safe autonomous operatio...

EUVD-2025-198528

Roo Code is an AI-powered autonomous coding agent that lives in users' editors. Prior to version 3.26.7, Due to an error in validation it was possible for Roo to automatically execute commands that did not match the allow list prefixes. This issue has been patched in version 3.26.7...

AI as Cyberattacker

From Anthropic: In mid-September 2025, we detected suspicious activity that later investigation determined to be a highly sophisticated espionage campaign. The attackers used AI’s “agentic” capabilities to an unprecedented degree­--using AI not just as an advisor, but to execute the cyberattacks...

It’s not personal, it’s just business

Welcome to this week's edition of the Threat Source newsletter. This week, we explore how advances in agentic AI are rapidly transforming the cyber crime business. Agentic AI programming gives AI agents autonomy, allowing them to interact with external systems to collect information, make decisio...

CVE-2025-10702

Improper Control of Generation of Code 'Code Injection' vulnerability in Progress DataDirect Connect for JDBC drivers, Progress DataDirect Open Access JDBC driver and Hybrid Data Pipeline allows Remote Code Inclusion. The SpyAttribute connection option implemented by the DataDirect Connect for JD...

Hiding in the AI Traffic: Abusing MCP for LLM-Powered Agentic Red Teaming

Generative AI is reshaping offensive cybersecurity by enabling autonomous red team agents that can plan, execute, and adapt during penetration tests. However, existing approaches face trade-offs between generality and specialization, and practical deployments reveal challenges such as...

​​Ambient and autonomous security for the agentic era​​

Over the past year, I've had countless conversations with customers who are striving to unlock human ambition with AI. They are on their journey to become Frontier Firms, where humans and agents push the boundaries of innovation and create new possibilities, empowering humans to become limitless...

Collaborative research by Microsoft and NVIDIA on real-time immunity

AI-Powered Threats Demand AI-Powered Defense While AI supports growth and innovation, it is also reshaping how organizations address faster, more adaptive security risks. AI-driven security threats, including “vibe-hacking”, are evolving faster than traditional defenses can adapt. Attackers can n...

T2I-Based Physical-World Appearance Attack against Traffic Sign Recognition Systems in Autonomous Driving

Traffic Sign Recognition TSR systems play a critical role in Autonomous Driving AD systems, enabling real-time detection of road signs, such as STOP and speed limit signs. While these systems are increasingly integrated into commercial vehicles, recent research has exposed their vulnerability to...

Scalable Hierarchical AI-Blockchain Framework for Real-Time Anomaly Detection in Large-Scale Autonomous Vehicle Networks

The security of autonomous vehicle networks is facing major challenges, owing to the complexity of sensor integration, real-time performance demands, and distributed communication protocols that expose vast attack surfaces around both individual and network-wide safety. Existing security schemes...

Chinese Hackers Use Anthropic's AI to Launch Automated Cyber Espionage Campaign

State-sponsored threat actors from China used artificial intelligence AI technology developed by Anthropic to orchestrate automated cyber attacks as part of a "highly sophisticated espionage campaign" in mid-September 2025. "The attackers used AI's 'agentic' capabilities to an unprecedented degre...

MAL-2025-170226 Malicious code in uyia-iaydut-daina (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 3a057e94b830ba8e1807669f78a8aacf36dd345bfc63d6b5001915c212d092b9 This package appears to be part of the tea.xyz token reward campaign that flooded npm. These packages typically contain autopublish scripts auto.js,...

Malicious code in citra-kacang10-riris (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 1324604dc829af15807a815e2a9e5fca09105d2daab82812cc52ff85b840370b This package appears to be part of the tea.xyz token reward campaign that flooded npm. These packages typically contain autopublish scripts auto.js,...

EUVD-2025-93135

Malicious code in autonomousmastodonz3n npm...

EUVD-2025-93136

Malicious code in autonomouscoyotez3n npm...

Malicious code in autonomous_whale_silver-17 (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 1f34fab54fc34a156613197b1cabe9637780df6fa3a09d2a239a75c22b05f787 This package appears to be part of the tea.xyz token reward campaign that flooded npm. These packages typically contain autopublish scripts auto.js,...

EUVD-2025-77719

Malicious code in autonomousminkz3n npm...

EUVD-2025-79776

Malicious code in autonomousparrotdumbs npm...

EUVD-2025-79774

Malicious code in autonomouswildfowldumbs npm...

Malicious code in hot_parrot_0xrequest (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 032532bf530b690f51afba08ec01f254202f8b2a069c21ce47f7fa85ed4dc0bc This package appears to be part of the tea.xyz token reward campaign that flooded npm. These packages typically contain autopublish scripts auto.js,...