Description-Code Inconsistency in Real-World MCP Servers: Measurement, Detection, and Security Implications

The Model Context Protocol MCP has emerged as a critical standard empowering Large Language Models LLMs to utilize external tools. In this ecosystem, LLMs rely on natural language descriptions provided by MCP servers to select and execute functions. This interaction implicitly assumes that tool...

Security, Privacy, and Ethical Risks in OpenClaw

This paper systematically investigates the security, privacy, and ethical risks, as well as the traceability challenges of OpenClaw, a locally executable AI agent system for natural language interaction and real-world task completion. While OpenClaw shows strong potential for personal assistance,...

Security of LLM-Generated Code: A Comparative Analysis

The majority of software developers use or are planning to use Artificial Intelligence AI tools in their development processes. Their top reasons include improving productivity and faster learning. In fact, Large Language Model LLM-generated code is currently in production, including in major tec...

Astra Linux - уязвимость в edk2

The example of an encrypted private key in EDK2, present in the IpSecDxe.efi, may pose potential security risks...

From AI-Generated Content to Agentic Action: Security and Safety Threats in Generative AI

Generative AI systems are increasingly used not only to produce content but also to retrieve data, invoke tools, and execute actions. This work examines the security and safety implications of that shift across content-level, model-level, and agentic threats. We analyze how attacker access...

CVE-2025-62316

Technical details are not publicly available in the provided documents. Monitor for updates on CVE-2025-62316 from the linked sources; no affected products, vectors, or remediation are stated.

How AI Hallucinations Are Creating Real Security Risks

AI hallucinations are introducing serious security risks into critical infrastructure decision-making by exploiting human trust through highly confident yet incorrect outputs. When an AI model lacks certainty, it doesn’t have a mechanism to recognize that. Instead, it generates the most probable...

Security Risks in Tool-Enabled AI Agents: A Systematic Analysis of Privileged Execution Environments

Tool-enabled AI agents are increasingly deployed in cloud-hosted environments and offered as services, where they perform side-effecting operations through privileged tools within execution environments. While such agents enable powerful automation, the security implications of hosting autonomous...

Heimdallr: Characterizing and Detecting LLM-Induced Security Risks in GitHub CI Workflows

GitHub Continuous Integration CI workflows increasingly integrate Large Language Models LLMs to automate review, triage, content generation, and repository maintenance. This creates a new attack surface: externally controllable workflow inputs can shape LLM prompts and outputs, which may in turn...

A week in security (April 27 – May 3)

Last week on Malwarebytes Labs: 3 easy-to-miss cybersecurity risks for small businesses Actively exploited cPanel bug exposes millions of websites to takeover More PayPal emails hijacked to deliver tech support scams Hackers stole hundreds of thousands of Roblox accounts: Here’s what to do...

Security Attack and Defense Strategies for Autonomous Agent Frameworks: A Layered Review with OpenClaw As a Case Study

Autonomous agent frameworks built upon large language models LLMs are evolving into complex, tool-integrated, and continuously operating systems, introducing security risks beyond traditional prompt-level vulnerabilities. As this paradigm is still at an early stage of development, a timely and...

The AI Threat Multiplier: Why Architectural Flaws Are the New Frontier

AI has put an end to the era of evaluating CVEs in isolation. The most critical risks now emerge when legacy state machines meet asynchronous execution...

poker-exploit-ai

No d...

Why Your Deprecated Endpoints Are an Attacker’s Best Friend: The Rise of Ghost APIs

Ghost APIs are deprecated endpoints left active, exposing systems to attack. Learn how they differ from shadow APIs and why they create hidden security risks...

AI Agents and Non-Human Identities Creating Critical Security Gaps, Report

New research from Keeper Security, reveals non-human identities and automated system-to-system interactions are becoming the top security risk for businesses in 2026...

Security Considerations for Artificial Intelligence Agents

This article, a lightly adapted version of Perplexity's response to NIST/CAISI Request for Information 2025-0035, details our observations and recommendations concerning the security of frontier AI agents. These insights are informed by Perplexity's experience operating general-purpose agentic...

Agentic AI security: Why you need to know about autonomous agents now

Agentic AI is making headlines worldwide for its potential force-multiplying capabilities, and organizations are understandably intrigued by how it can improve throughput and capabilities. However, as with any technological revolution, unforeseen issues are inevitable, and agentic AI is no...

The Attack and Defense Landscape of Agentic AI: A Comprehensive Survey

AI agents that combine large language models with non-AI system components are rapidly emerging in real-world applications, offering unprecedented automation and flexibility. However, this unprecedented flexibility introduces complex security challenges fundamentally different from those in...

Microsoft Azure Linux Virtual Machines 安全漏洞

Microsoft Azure Linux Virtual Machines are cloud computing infrastructure resources provided by Microsoft. They are on-demand, elastic, and support multiple mainstream Linux distributions. There are security vulnerabilities associated with Microsoft Azure Linux Virtual Machines. Attackers can...

LLM-Enabled Applications Require System-Level Threat Monitoring

LLM-enabled applications are rapidly reshaping the software ecosystem by using large language models as core reasoning components for complex task execution. This paradigm shift, however, introduces fundamentally new reliability challenges and significantly expands the security attack surface, du...