All news with #agent security tag

🛡️ An enterprise sales team built an AI agent to manage renewals; the agent reads emails, queries CRM data, drafts responses, and updates records. This workflow combines private data, untrusted input, and external communication, changing the security model. Traditional controls like IAM and DLP still matter but are insufficient alone. Runtime, context-aware controls that inspect prompts, outputs, and tool calls are required to prevent prompt injection, data exfiltration, and unsafe actions.

🔒 Varonis tested an OpenClaw-based AI agent named Pinchy with access to a controlled Google Workspace to see whether autonomous agents could be phished. The agent was given Gmail access plus mock AWS credentials, CRM exports, internal chats, and calendars, and it still leaked credentials and customer data in scenarios that mimicked routine colleague requests. A stricter safety profile improved performance, but the agent still failed when social trust cues were abused. Researchers say the problem stems from architecture and governance gaps, urging enforceable controls, identity segregation, and human review for sensitive requests.

📧 Researchers at Varonis tested an OpenClaw AI email agent connected to Gmail, browser tools, and internal data sources and found it vulnerable to common phishing techniques. The agent ran in both generic and strict configurations and used Google Gemini 3.1 Pro and OpenAI GPT-5.4 models. While the agent detected malicious links and OAuth apps, it still exfiltrated credentials and CRM data in scenarios exploiting identity verification failures. Varonis recommends explicit sender verification, restricted external emailing, and human approval for high-risk actions.

🤖 Microsoft has integrated Anthropic’s Claude Fable 5 into Foundry, bringing Mythos-level capabilities to GitHub Copilot and Foundry Agent Service with enterprise-grade safeguards. The model excels at long-running, multi-stage tasks—code refactors, deep research, and document-heavy workflows—while Foundry adds governance, observability, and deployment controls. Combined with Microsoft IQ, Fable 5 can reason across organizational data and applications to support production-grade autonomous agents.

🛡️ Google details how Google Security Operations pairs with Google AI Threat Defense to detect, investigate, and contain AI-accelerated attacks across cloud and enterprise environments. The post explains three specialized agents — Detection Engineering, Triage and Investigation, and Threat Hunting — that translate threat intelligence into custom detections, autonomously investigate alerts, and proactively hunt stealthy compromises. These agents use diverse telemetry, simulated events, and AI-driven automation to reduce time-to-detection and speed remediation, addressing gaps where patching is impossible or delayed.

🛡️ Researchers at the University of Toronto built an AI-driven worm prototype that autonomously discovered and exploited vulnerabilities across a simulated enterprise network. Using a locally hosted, free LLM and a custom agentic harness, the worm self-replicated to multiple systems by chaining old and recent CVEs and common misconfigurations. Over several days it spread to most targets, demonstrating that attackers do not need cutting-edge models to mount damaging, adaptive attacks. The findings underscore the need for faster patching, AI-assisted defensive testing, and improved architecture such as segmentation and zero trust.

🖥️ Amazon Bedrock AgentCore Runtime introduces the InvokeAgentRuntimeCommandShell API, providing a persistent, PTY-backed terminal over WebSocket into running agent sessions. This complements existing one-shot execution via InvokeAgentRuntimeCommand and delivers a full terminal experience inside an isolated microVM with features like colors, tab completion, Ctrl+C, resize, and automatic reconnect. Developers hosting coding agents (for example, Claude Code, OpenAI Codex, Amazon Kiro) can now authenticate, drop into the agent microVM, inspect files, run ad-hoc commands, and debug while retaining session state across reconnects. Each interactive session uses a runtime session ID and shell ID for resume; up to 10 concurrent shells are supported per runtime.

🔍 Microsoft has expanded its Taxonomy of Failure Modes in Agentic AI Systems with seven newly identified ways agentic AI can be compromised. The update cites rapid adoption, maturation of the Model Context Protocol (MCP) ecosystem, proliferation of computer-use agents, and increased empirical evidence as drivers. New failure modes include supply chain compromise, goal hijacking, inter-agent trust escalation, visual attacks on CUAs, session context contamination, MCP/plugin abuse, and capability disclosure. Microsoft recommends inventorying agent supply chains, issuing cryptographic attestations, adding these modes to red-team exercises, and auditing human-in-the-loop controls.

🛡️ Lloyds Banking Group treats agentic AI as an engineering problem to be designed, constrained and tested at scale. At OWASP’s GenAI Security Summit, Lloyds’ security leads explained an “AI safe adoption” strategy spanning lifecycle governance, an internal agent marketplace, and multidisciplinary feature teams. Key challenges include agent identity, runtime observability and automated red‑teaming, while prioritizing low‑risk, high‑value use cases for customers.

🛡️ The Open Worldwide Application Security Project (OWASP) published a new agentic AI security maturity framework in the GenAI Security Project paper "State of Agentic AI Security and Governance" on June 3, and introduced it at Infosecurity Europe 2026 on June 4. The Enterprise Adoption Maturity Model maps deployments (from shadow AI to multi-agent systems) against governance maturity (from ad hoc to continuous oversight). It provides a decision tool to identify mismatches and prescribes either tailored controls for agentic systems or constrained agent permissions until governance catches up.

🚀 This tutorial shows how to build an AI agent with Google’s Agent Development Kit (ADK), containerize it, and deploy it to GKE Autopilot using Vertex AI (Gemini) as the model backend. It walks through local testing, creating a multi-stage Docker image, pushing to Artifact Registry, and configuring a Kubernetes Deployment and Service. The guide emphasizes secure authentication with Workload Identity and exposes the agent via the Kubernetes Gateway API with a Google-managed TLS certificate.

🔒 Microsoft announced new controls to contain agentic AI workloads, including the Microsoft Execution Container (MXC) runtime and enhancements to the multi-agent vulnerability research system MDASH. MXC is a policy-driven sandbox for specifying and enforcing access to files, networks, credentials, and resources at runtime across Windows, Linux, and macOS. The company also highlighted Agent 365 SDK, Windows 365 for Agents, and two open-source standards—ASSERT and Agent Control Specifications—to govern agent behavior across platforms.

🛡️ This article explains why AI requires a unified security architecture — the AI Defense Plane — to discover, protect, govern, and assure AI behavior across employees, applications, and agents. It describes how AI becomes an execution layer that can retrieve data, call tools, and take actions, creating risks that traverse traditional security boundaries. The piece emphasizes runtime protection, coordinated enforcement, and continuous testing to prevent prompt-based attacks, data exposure, and unsafe agent behavior.

🔒 At Microsoft Build 2026, Microsoft announced new security capabilities to integrate protection across the development lifecycle, addressing insecure code, agent proliferation, and model risk. The expanded preview of the multi-model agentic scanning harness (codename MDASH) integrates with Microsoft Defender to orchestrate hundreds of AI agents for exploit discovery. New tools such as Agent 365, MXC SDK, and Purview enhancements provide runtime controls, data protection, and governance to help developers and security teams act earlier and with consistent oversight.

🛡️ The Remote Model Context Protocol (MCP) Server for AlloyDB is now generally available, providing a secure HTTP endpoint that lets AI agents access real-time operational data. This fully managed service simplifies production deployments by centralizing discovery, offering fine-grained IAM-based authorization, audit logging, and integration with Model Armor for prompt and response protection. Developers can join AlloyDB operational data with analytics in BigQuery and use built-in AI functions for low-latency agentic experiences.

🧭 At Infosecurity Europe 2026, OWASP will unveil the Agentic Research Council to better align fast‑moving agentic AI capabilities with security research and operational practice. Launched from the GenAI Security Project’s Agentic Security Initiative, the council will prioritize a public research pipeline, convene working groups and connect academic outputs to deployable mitigations. The initiative aims to accelerate runtime‑focused defenses against multi‑agent threats.

🛰️ The Linux Foundation has proposed DNS-AID, a standards-driven extension to the Domain Name System to let AI agents discover, verify, and communicate without new infrastructure. The project leverages a well-known DNS address pattern (for example, _index._agents.{domain}) to provide a global, vendor-neutral directory for agents and MCP servers. Initial work was done by Infoblox, with contributions from Deutsche Telekom and Amazon, and the foundation is soliciting further input to keep the approach scalable and secure.

🧭This post explains how A2UI, an open protocol for agent-driven user interfaces, enables agents to return structured JSON UI payloads instead of plain text or HTML. It outlines the four-layer stack (app shell, rendering, conversation pipeline, and cargo), the inline and decoupled patterns, and how Gemini Enterprise integrates a built-in A2UI renderer. The article points to a reference repo, demo, and implementation notes for registering an A2A agent with GE.

🔒 Palo Alto Networks has completed its acquisition of Portkey and will integrate Portkey’s AI Gateway into Prisma AIRS to provide a centralized control plane that secures and governs AI agents at scale. The integrated Prisma AIRS AI Gateway will offer unified APIs, an agent registry, semantic routing, artifact scanning, automated red teaming and runtime security to identify, authenticate and authorize agent interactions in real time. This aims to give enterprises a single enforcement point to manage agent identity, least-privilege access and consistent policies across autonomous workloads.

🛡️ CIOs rushing to deploy AI agents without visibility risk major failures; experts warn that observability and governance are required. Many organizations treat agents like RPA and set-and-forget systems, but agents operate in model runtimes and need end-to-end tracing, least-privilege permissions, and human-in-the-loop checks. Vendors and cloud providers offer tools, yet governance can become a bottleneck if it’s not scalable and actionable.