Security of 100 AI Agents Tested and Ranked – What You Need to Know 2026-06-03 at 20:19 By Kevin Townsend The AI Risk Quadrant evaluates AI agents based on three factors: how vulnerable they are to compromise, the potential impact of a breach, and the strength of their security defenses. The post Security of 100 […]
Security of 100 AI Agents Tested and Ranked – What You Need to Know Read More »
Only 11% of production agents pass the AI agent security bar 2026-06-03 at 14:00 By Mirko Zorz Enterprise teams are running AI agents that write code, drive browsers, answer customer calls, manage cloud infrastructure, and query data warehouses with standing credentials. A new independent assessment of 100 production agents finds that nearly all of them
Only 11% of production agents pass the AI agent security bar Read More »
Microsoft Scout agent opens a new category of always-on Autopilots 2026-06-03 at 11:28 By Anamarija Pogorelec Workplace AI assistants have mostly waited for a prompt before doing anything. A user asks, the tool answers, and the exchange ends there. Microsoft is putting a different kind of agent inside its Office applications, one designed to keep
Microsoft Scout agent opens a new category of always-on Autopilots Read More »
NVIDIA goes open source with a big batch of physical AI agent tools 2026-06-01 at 11:46 By Anamarija Pogorelec NVIDIA just dropped a big batch of open-source “physical AI” skills and tools, and they’re designed to make a roboticist’s life a whole lot easier. The idea? Take the messy, complicated work behind robots, self-driving cars,
NVIDIA goes open source with a big batch of physical AI agent tools Read More »
OWASP Agent Memory Guard: Stop AI agents from being weaponized through their own memory 2026-06-01 at 08:19 By Mirko Zorz AI agents keep memory across sessions. Conversation history, vector stores, scratchpads, and RAG indexes persist between runs, and anything written into that store becomes a privileged input the agent reads back later. An attacker who
OWASP Agent Memory Guard: Stop AI agents from being weaponized through their own memory Read More »
Google AI Threat Defense targets attackers using AI to find flaws faster 2026-05-27 at 17:23 By Anamarija Pogorelec Google Cloud introduced AI Threat Defense, an automated cybersecurity platform that combines several of the company’s security assets to find, prioritize, and patch software vulnerabilities at machine speed. The product is aimed at enterprises contending with attackers
Google AI Threat Defense targets attackers using AI to find flaws faster Read More »
Microsoft open-sources tools for designing and testing AI agents 2026-05-21 at 19:15 By Zeljka Zorz Microsoft has open-sourced two tools aimed at bringing security discipline to AI agent development: Clarity, a structured design review tool, and RAMPART, a continuous testing framework. The release comes from Microsoft’s AI Red Team, the company’s internal unit that stress-tests
Microsoft open-sources tools for designing and testing AI agents Read More »
AI red teaming agents change how LLMs get tested 2026-05-21 at 08:00 By Mirko Zorz Adversarial probing of LLMs has piled up a sprawling toolkit over the past three years. Attack techniques with names like Tree of Attacks with Pruning, Crescendo, and Skeleton Key sit alongside hundreds of prompt transforms and scoring methods across open-source
AI red teaming agents change how LLMs get tested Read More »
When your AI assistant has the keys to production 2026-05-20 at 09:34 By Sinisa Markovic Large language models in operational roles query telemetry, propose configuration changes, and in some deployments execute those changes against live infrastructure. Ticket drafting and alert summarization were the starting point. Vendors describe this work as autonomous remediation or self-healing infrastructure.
When your AI assistant has the keys to production Read More »
AI shrinks vulnerability exploitation window to hours 2026-05-18 at 09:42 By Anamarija Pogorelec Time has become organizations’ biggest vulnerability because the gap between vulnerability discovery and exploitation has narrowed to hours, according to Synack’s 2026 State of Vulnerabilities Report. Total vulnerabilities by severity (2022-2025) (Source: Synack) AI expands the attack surface Agentic AI systems that
AI shrinks vulnerability exploitation window to hours Read More »
Lyrie: Open-source autonomous pentesting agent 2026-05-18 at 09:42 By Sinisa Markovic Penetration testing has usually required weeks of manual work, specialized tooling, and teams with narrow skill sets. Lyrie, an open-source autonomous security agent built by OTT Cybersecurity, compresses that process into a command line tool and publishes the entire codebase. The project reached version
Lyrie: Open-source autonomous pentesting agent Read More »
Microsoft turns Copilot Studio into an AI agent control center 2026-05-14 at 18:25 By Anamarija Pogorelec The Microsoft Copilot Studio April 2026 updates improve visibility and governance for admins and expand workflow capabilities for managing agents. Copilot surfaces agent status in the authoring experience, giving admins insight into each agent’s security and protection posture. Customers
Microsoft turns Copilot Studio into an AI agent control center Read More »
One in four MCP servers opens AI agent security to code execution risk 2026-05-05 at 13:21 By Anamarija Pogorelec Enterprise deployments of AI agents lean on two extension mechanisms that introduce risk at different layers of the stack. MCP servers expose deterministic code functions with structured, loggable invocations. Skills load textual instruction sets directly into
One in four MCP servers opens AI agent security to code execution risk Read More »
Pipelock: Open-source AI agent firewall 2026-05-04 at 09:46 By Mirko Zorz AI coding agents run with shell access, environment variables containing API keys, and unrestricted internet connectivity, creating a single point of failure where one compromised tool call can leak credentials to an attacker-controlled domain. Pipelock, an open-source security harness developed by Joshua Waldrep under
Pipelock: Open-source AI agent firewall Read More »
FIDO Alliance wants to keep AI agents from going rogue on online payments 2026-04-29 at 05:30 By Sinisa Markovic AI agents are beginning to shop, log in, and complete tasks with little direct input. That shift is pushing the security industry to rethink how trust works when actions are carried out on a user’s behalf.
FIDO Alliance wants to keep AI agents from going rogue on online payments Read More »
The AI criminal mastermind is already hiring on gig platforms 2026-04-27 at 10:30 By Mirko Zorz Labor-hire platforms let anyone with a credit card post a task and pay a stranger to complete it. The RentAHuman platform extends that model to AI agents through a Model Context Protocol server, allowing an agent to post gigs
The AI criminal mastermind is already hiring on gig platforms Read More »
Indirect prompt injection is taking hold in the wild 2026-04-24 at 23:26 By Zeljka Zorz The open web is slowly but surely filling up with “traps” designed for LLM-powered AI agents. The technique, known as indirect prompt injection (IPI), involves hiding (more or less) covert instructions inside ordinary web pages, waiting for an AI agent
Indirect prompt injection is taking hold in the wild Read More »
Why Cybersecurity Must Rethink Defense in the Age of Autonomous Agents 2026-04-24 at 16:23 By Torsten George From autonomous code generation to decision-making systems that initiate actions without human intervention, the industry is entering a new phase. The post Why Cybersecurity Must Rethink Defense in the Age of Autonomous Agents appeared first on SecurityWeek. This
Why Cybersecurity Must Rethink Defense in the Age of Autonomous Agents Read More »
Scenario: Open-source framework for automated AI app red-teaming 2026-04-23 at 09:47 By Mirko Zorz Enterprises running customer service bots, data analytics agents, and other AI-driven applications in production handle sensitive records and connect to core business systems every day. LangWatch has released Scenario, an open-source framework that runs automated red-team exercises against AI agents using
Scenario: Open-source framework for automated AI app red-teaming Read More »
Tencent’s QClaw AI agent app arrives on Windows and macOS 2026-04-22 at 13:48 By Sinisa Markovic Tencent has opened an international beta of QClaw, an AI agent application aimed at consumers in Canada, Japan, Singapore, South Korea, and the United States. The first wave is capped at 20,000 users. Additional markets are scheduled to follow.
Tencent’s QClaw AI agent app arrives on Windows and macOS Read More »