AI agents

A security startup, depthfirst, reported 21 zero-day vulnerabilities in FFmpeg found by its autonomous AI security agent, each with a reproducible proof-of-concept input, at a cost of around $1,000. The same week, Google shipped Chrome 149 with fixes for 429 security bugs, a record for a single release, though Google did not tie that count to AI.

Microsoft has identified seven new failure modes in agentic AI systems, extending the first Taxonomy of Failure Modes in Agentic AI Systems it published last year. The new modes include Goal Hijacking, Inter-Agent Trust Escalation, Computer Use Agent (CUA) Visual Attack, and MCP / Plugin Abuse. Microsoft attributes the expanding list to rapid mainstream adoption, the maturing Model Context Protocol (MCP) ecosystem, the rise of computer-use agents, and more empirical findings from real-world research.

Researchers say AI worms, described as "viruses with wings and brains," can adapt to new environments and seek out vulnerabilities. They are likely to strike within a year.

CrowdStrike and NVIDIA's collaboration on securing autonomous agents is cited as part of industry efforts to define secure agentic AI at scale. The article argues that organizations should treat AI agents as privileged identities, secure the full AI lifecycle from build to runtime, and use AI to defend against AI-driven threats.

Microsoft's AI Red Team has published v2.0 of its Taxonomy of Failure Modes in Agentic AI Systems, updating the April 2025 v1.0. The update adds seven new failure mode categories, expands the mitigations section, and draws on 12 months of red team engagements against deployed agentic systems. It cites open-source frameworks such as OpenClaw, where CVE-2026-25253 was a one-click RCE via WebSocket hijacking, and 99 CVEs published in 2025 for MCP-related software.

Dave Wajsgras, CEO of Everfox, argues in a contributed piece that agentic AI in defense networks needs secure infrastructure to deliver its benefits. He cites a reported but unconfirmed claim that an unauthorized group gained access to Anthropic's Claude Mythos model within hours of its limited technical preview. He names three areas to secure: what enters the model, who and what can access it, and where AI agents reach back out.

Willow, formerly Webrix, emerged from stealth with an identity and access platform for enterprise AI agents and $7 million in seed funding from Hetz Ventures and executives at Wix. The platform acts as a centralized gateway for tools such as Claude, Gemini, and ChatGPT, assigns a verifiable identity to each AI agent through identity providers such as Okta and Entra, and enforces least-privilege access controls at runtime.

Endava, a global technology services company, has made OpenAI its enterprise AI platform, giving employees ChatGPT Enterprise and Codex access. The company has embedded OpenAI technology across its DavaFlow lifecycle, from meeting preparation and planning to software engineering and deployment, and has extended AI agents into legal, finance and operations work.

Morgan Stanley will soon let clients' autonomous AI agents pull data and insights directly from its ShareWorks and Equity Edge stock administration platforms, bypassing interfaces built for human users, according to Mark Mitchell, the firm's chief product officer for Morgan Stanley at Work. The bank has granted early agentic access to a handful of clients and plans to open it to its 3,400 administration clients by next year. The firm relies on the Model Context Protocol to make this connection.

Meta announced Meta Business Agent, a feature that lets businesses use AI agents across WhatsApp, Messenger and Instagram to answer customer questions, recommend products and book appointments. It will be part of a business-focused subscription tier within Meta One, and businesses on WhatsApp Business Platform will be charged on a consumption basis. The move aims to diversify Meta's revenue, which still relies on ads for about 98% of income.

Adversa AI tested and ranked 100 AI agents across ten categories, placing them on a new AI Risk Quadrant. Only 11 were rated 'capable well-defended', and 98% of the agents have what Adversa calls the 'lethal trifecta': private data access, exposure to untrusted content, and the ability for outbound actions. The analysis describes a 'power-protection inversion', where the most capable agents also carry the widest attack surface, with computer agents and coding agents showing the greatest inversion.

At Microsoft Build, Microsoft announced Microsoft Execution Container (MXC), a runtime containment offering for agentic AI workloads, and updates to its multi-agent vulnerability research system MDASH. MXC is a policy-driven execution workflow that lets developers specify what an AI agent can access, such as files, networks, resources and credentials, and enforces those boundaries at runtime. OpenClaw and NVIDIA's OpenShell are already adopting MXC.

The source argues that high-autonomy AI agents with broad permissions and unfettered access create serious risk. It urges enterprises to act now before such agents cause a damaging incident.

Microsoft announced Project Solara at Build 2026, a new operating system built on Android rather than Windows, designed for gadgets that run AI agents. The company demonstrated two concept devices: a desk device resembling an Amazon Echo Show that unlocks with facial recognition, and a wearable badge with a camera and fingerprint scanner that can wake an AI agent.

AWS describes how SaaS providers can use resource-based policies on Amazon Bedrock AgentCore to control access to a shared AgentCore Runtime and its endpoint per tenant. The post walks through a multi-tenant customer service platform where one tenant gets cross-account access from its own AWS account, while another is restricted to invocations from a private VPC for regulatory compliance.

Google has launched Spark, a new always-on AI agent positioned as its agentic answer to general-purpose assistance. The source text is an excerpt from a Verge review that describes the reviewer's trip-planning experience with the product, but the excerpt cuts off before the full assessment.

KPMG reports that 68% of health-care providers have adopted AI agents into their workforce. At Hospital for Special Surgery, AI agents process insurance claims at 1,100 per month, cutting the appeals stage from 45 minutes to five and raising the appeal success rate from 65% to 100% in nine months. HSS is also deploying an AI scheduling and triage service, built with Ema Unlimited, that escalates sensitive or uncertain cases to human specialists.

Google's Gemini Spark, an AI agent that Google says can run multi-step tasks in the background, was tested by a reviewer who found it impressively capable. The reviewer questions whether it is worth its financial cost and potential privacy tradeoffs.