301 matches found
Agentic AI’s OODA Loop Problem
The OODA loop --for observe, orient, decide, act--is a framework to understand decision-making in adversarial situations. We apply the same framework to artificial intelligence agents, who have to make their decisions with untrustworthy observations and orientation. To solve this problem, we need...
Bringing the Power of Agentic AI for Identity Risk, Adaptive Threat Prioritization, and Exposure Exploitability Validation
Qualys Enterprise TruRisk Management ETM extends the power of risk operations with agentic AI — Introducing ETM Identity, TruLens for industry-based threat prioritization, and TruConfirm exposure exploitability validation to accelerate your remediation. Every year at our yearly conference, now...
In-Browser LLM-Guided Fuzzing for Real-Time Prompt Injection Testing in Agentic AI Browsers
Large Language Model LLM based agents integrated into web browsers often called agentic AI browsers offer powerful automation of web tasks. However, they are vulnerable to indirect prompt injection attacks, where malicious instructions hidden in a webpage deceive the agent into unwanted actions...
From Prompts to Protocols: How Agentic Systems, MCP, Vibe Coding, and Schema-Aware Tools Are Rewiring Software Engineering
Modern software engineering faces growing complexity across codebases, environments, and workflows. Traditional tools, although effective, rely heavily on…...
The AI SOC Stack of 2026: What Sets Top-Tier Platforms Apart?
The SOC of 2026 will no longer be a human-only battlefield. As organizations scale and threats evolve in sophistication and velocity, a new generation of AI-powered agents is reshaping how Security Operations Centers SOCs detect, respond, and adapt. But not all AI SOC platforms are created equal...
A Survey on Agentic Security: Applications, Threats and Defenses
The rapid shift from passive LLMs to autonomous LLM-agents marks a new paradigm in cybersecurity. While these agents can act as powerful tools for both offensive and defensive operations, the very agentic context introduces a new class of inherent security risks. In this work we present the first...
Agentic Misalignment: How LLMs Could Be Insider Threats
We stress-tested 16 leading models from multiple developers in hypothetical corporate environments to identify potentially risky agentic behaviors before they cause real harm. In the scenarios, we allowed models to autonomously send emails and access sensitive information. They were assigned only...
EUVD-2025-29000
Malicious code in bioql PyPI...
PentestMCP: A Toolkit for Agentic Penetration Testing
Agentic AI is transforming security by automating many tasks being performed manually. While initial agentic approaches employed a monolithic architecture, the Model-Context-Protocol has now enabled a remote-procedure call RPC paradigm to agentic applications, allowing for the flexible constructi...
How Agentic AI Powers Seamless Audit Readiness with Agent Chang
Audits are rarely simple. Security and compliance teams often find themselves buried in repetitive, time-consuming tasks—collecting logs from multiple systems, exporting reports from various tools, and manually reconciling data in spreadsheets. Evidence must be traced back to the correct controls...
Empowering defenders in the era of agentic AI with Microsoft Sentinel
Microsoft unveils a new wave of security innovation—delivering an agentic platform to protect organizations at scale We are living through a turning point in how organizations work and defend themselves. Across industries, “Frontier Firms” are emerging; these are businesses where humans and AI...
Microsoft Expands Sentinel Into Agentic Security Platform With Unified Data Lake
Microsoft on Tuesday unveiled the expansion of its Sentinel Security Incidents and Event Management solution SIEM as a unified agentic platform with the general availability of the Sentinel data lake. In addition, the tech giant said it's also releasing a public preview of Sentinel Graph and...
ChatGPT Deep Research zero-click vulnerability fixed by OpenAI
OpenAI has moved quickly to patch a vulnerability known as “ShadowLeak” before anyone detected real-world abuse. Revealed by researchers yesterday, ShadowLeak was an issue in OpenAI’s Deep Research project that attackers could exploit by simply sending an email to the target. Deep Research was...
Security Update for Microsoft Visual Studio Code (September 2025)
The version of Microsoft Visual Studio Code installed on the remote host is prior to 1.104.0. It is, therefore, affected by multiple vulnerabilities: - Ai command injection in Agentic AI and Visual Studio Code allows an unauthorized attacker to execute code over a network. CVE-2025-55319 Note tha...
CVE-2025-55319
Ai command injection in Agentic AI and Visual Studio Code allows an unauthorized attacker to execute code over a network...
AI browsers or agentic browsers: a look at the future of web surfing
Browsers like Chrome, Edge, and Firefox are our traditional gateway to the internet. But lately, we have seen a new generation of browsers emerge. These are AI-powered browsers or "agentic browsers"—which are not to be confused with your regular browsers that have just AI-powered plugins bolted o...
CVE-2025-55319
Ai command injection in Agentic AI and Visual Studio Code allows an unauthorized attacker to execute code over a network...
CVE-2025-55319
Ai command injection in Agentic AI and Visual Studio Code allows an unauthorized attacker to execute code over a network...
CVE-2025-55319
CVE-2025-55319 corresponds to a remote code execution issue involving Agentic AI in Microsoft Visual Studio Code. The vulnerability allows an unauthenticated, network-based attacker to execute arbitrary code on the affected host via the Agentic AI functionality integrated with VS Code. The CVE is...
