Coverage tagged "MCP".
arXiv:2610.36108v1 Announce Type: new Abstract: LLM agents increasingly access external tools through the Model Context Protocol (MCP), but the natural-language metadata used to describe those tools…
arXiv:2610.36626v1 Announce Type: new Abstract: Third-party community-based bots are central to how social platforms such as Discord work. They moderate content, manage roles, play music, and support…
FireMon has announced FireMon Agentic AI, changing how enterprises investigate network access, make policy decisions, and prepare security changes. Built into FireMon’s network security management…
arXiv:2610.33198v1 Announce Type: new Abstract: A neural classifier can fail completely inside a layered defense without any end-to-end number moving. We demonstrate this on BARBICAN, a fail-closed…
arXiv:2610.33633v1 Announce Type: new Abstract: Agents select tools by copyable descriptions, which cannot establish which implementation runs. ProbeID compares canonicalized responses to…
AI Agents Don’t Stop at the Device. Your Security Program Shouldn’t Either. October 26, 2026 GuidePoint Security By Chris Hughes, VP Security Strategy, Noma BLOG 5 min.
arXiv:2610.31974v1 Announce Type: new Abstract: Agentic AI systems using the Model Context Protocol (MCP) are vulnerable to indirect prompt injection through untrusted tool outputs. We demonstrate…
Donating Agent Skills to the Agentic AI Foundation News today from Anthropic: We’re committed to keeping Agent Skills open, community-driven, and vendor-neutral. Today, we are donating the standard…
Shadow AI used to be confined to a few simple scenarios, such as AI chatbots and AI browser extensions. Today, it spans a broad spectrum of complex vectors, making it harder to detect and control. In…
A flaw in the OpenCode AI coding agent allowed a malicious or hijacked MCP server to run code on a developer's Windows or WSL machine when the developer signed in. OpenCode connects to MCP (Model…
Delinea has announced Delinea Fastpath MCP Server, a new capability that connects access governance data to the AI assistants teams already use. Using the Model Context Protocol (MCP), finance, IT…
arXiv:2610.28810v1 Announce Type: new Abstract: The widespread adoption of generative artificial intelligence in recent years has brought a parallel rise in prompt injection and jailbreak attacks. By…
AI can write code and pass the bar exam, but it still struggles to buy a pair of shoes online. That’s because websites were built for humans, not agents. Most agents that shop for someone today work…
Key Findings Antidetect browsers obscure the digital identity of their users, enabling a single operator to silently manage thousands of isolated accounts across multiple platforms (including…
SOCRadar Threat Research Unit (STRU) has uncovered an AI-driven intrusion ecosystem run by affiliates of the INC Ransomware and The Gentlemen Ransomware groups. A single publicly accessible…
arXiv:2610.22828v1 Announce Type: new Abstract: Memory poisoning and decomposition attacks distribute malicious evidence across the operations of large language model agents. Existing request-level…
A seller on a restricted criminal forum is marketing an autonomous hacking tool that runs on stolen OpenAI, Anthropic and Google API keys, so the key’s owner pays for the scans. Bitsight’s threat…
Posted by Enxin Xie on Oct 15 Severity: moderate Affected versions: - Apache Answer through 2.0.2 Description: Missing Authorization vulnerability in Apache Answer. This issue affects Apache Answer…
Here’s a look at the most interesting products from the past week, featuring releases from NinjaOne, Qualys, Scytale, and SolarWinds. NinjaOne combines Katana AI and MCP server to accelerate IT…
arXiv:2610.20902v1 Announce Type: new Abstract: LLM coding agents such as Claude Code and OpenAI Codex can drive penetration-testing tools, but they reason about an engagement as a flat list of…
