Securing GenAI Multi-Agent Systems against Tool Squatting: a Zero Trust Registry-Based Approach

The rise of generative AI GenAI multi-agent systems MAS necessitates standardized protocols enabling agents to discover and interact with external tools. However, these protocols introduce new security challenges, particularly; tool squatting; the deceptive registration or representation of tools...

LLMpatronous: Harnessing the Power of LLMs for Vulnerability Detection

Despite the transformative impact of Artificial Intelligence AI across various sectors, cyber security continues to rely on traditional static and dynamic analysis tools, hampered by high false positive rates and superficial code comprehension. While generative AI offers promising automation...

New whitepaper outlines the taxonomy of failure modes in AI agents

We are releasing a taxonomy of failure modes in AI agents to help security professionals and machine learning engineers think through how AI systems can fail and design them with safety and security in mind. The taxonomy continues Microsoft AI Red Team's work to lead the creation of systematizati...

New whitepaper outlines the taxonomy of failure modes in AI agents

We are releasing a taxonomy of failure modes in AI agents to help security professionals and machine learning engineers think through how AI systems can fail and design them with safety and security in mind. The taxonomy continues Microsoft AI Red Team's work to lead the creation of systematizati...

DoomArena: a Framework for Testing AI Agents against Evolving Security Threats

We present DoomArena, a security evaluation framework for AI agents. DoomArena is designed on three principles: 1 It is a plug-in framework and integrates easily into realistic agentic frameworks like BrowserGym for web agents and $τ$-bench for tool calling agents; 2 It is configurable and allows...

Florida Man Enters the Encryption Wars

Plus: A US judge rules against police cell phone “tower dumps,” China names alleged NSA agents it says were involved in cyberattacks, and Customs and Border Protection reveals its social media spying tools...

Trusted Identities for AI Agents: Leveraging Telco-Hosted ESIM Infrastructure

The rise of autonomous AI agents in enterprise and industrial environments introduces a critical challenge: how to securely assign, verify, and manage their identities across distributed systems. Existing identity frameworks based on API keys, certificates, or application-layer credentials lack t...

On the Feasibility of Using MultiModal LLMs to Execute AR Social Engineering Attacks

Augmented Reality AR and Multimodal Large Language Models LLMs are rapidly evolving, providing unprecedented capabilities for human-computer interaction. However, their integration introduces a new attack surface for social engineering. In this paper, we systematically investigate the feasibility...

X-Teaming: Multi-Turn Jailbreaks and Defenses with Adaptive Multi-Agents

Multi-turn interactions with language models LMs pose critical safety risks, as harmful intent can be strategically spread across exchanges. Yet, the vast majority of prior work has focused on single-turn safety, while adaptability and diversity remain among the key challenges of multi-turn...

The Obvious Invisible Threat: LLM-Powered GUI Agents' Vulnerability to Fine-Print Injections

A Large Language Model LLM powered GUI agent is a specialized autonomous system that performs tasks on the user's behalf according to high-level instructions. It does so by perceiving and interpreting the graphical user interfaces GUIs of relevant apps, often visually, inferring necessary sequenc...

The Identities Behind AI Agents: A Deep Dive Into AI & NHI

AI agents have rapidly evolved from experimental technology to essential business tools. The OWASP framework explicitly recognizes that Non-Human Identities play a key role in agentic AI security. Their analysis highlights how these autonomous software entities can make decisions, chain complex...

The API Security Challenge in AI: Preventing Resource Exhaustion and Unauthorized Access

Agentic AI is transforming business. Organizations are increasingly integrating AI agents into core business systems and processes, using them as intermediaries between users and these internal systems. As a result, these organizations are improving efficiency, automating routine tasks, and drivi...

AutonomyAI Emerges from Stealth with $4M Pre-Seed Funding to Transform Front-End Development with Autonomous AI Agents

The first-of-its-kind solution integrates with company codebases, enabling AI agents to work in-context and generate production-grade, front-end code in minutes...

Jenkins 安全漏洞

Jenkins is a Jenkins open source application. An open source automation server Jenkins provides hundreds of plugins to support building, deploying and automating any project. A security vulnerability exists in Jenkins 2.503 and earlier and LTS 2.492.2 and earlier, which stems from a lack of...

Zulip server 安全漏洞

Zulip server is an open source team chat application from Zulip, Inc. in the United States. A security vulnerability exists in Zulip server versions prior to 10.0, which stems from a data export feature that discloses private data, including user agent types and private channel subject headings...

RHEL 9 : fence-agents (RHSA-2025:3113)

The remote Redhat Enterprise Linux 9 host has packages installed that are affected by a vulnerability as referenced in the RHSA-2025:3113 advisory. The fence-agents packages provide a collection of scripts for handling remote power management for cluster devices. They allow failed or unreachable...

RHEL 9 : fence-agents (RHSA-2025:3111)

The remote Redhat Enterprise Linux 9 host has packages installed that are affected by a vulnerability as referenced in the RHSA-2025:3111 advisory. The fence-agents packages provide a collection of scripts for handling remote power management for cluster devices. They allow failed or unreachable...

Malicious code in agents-kit (PyPI)

--- -= Per source details. Do not edit below this line.=-...

MAL-2025-2930 Malicious code in agents-kit (PyPI)

--- -= Per source details. Do not edit below this line.=-...

AI Agents and API Security: The Hidden Risks Lurking in Your Business Logic

Modern organizations are becoming increasingly reliant on agentic AI, and for good reason: AI agents can dramatically improve efficiency and automate mission-critical functions like customer support, sales, operations, and even security. However, this deep integration into business processes...