TLDRocket
Sign in

Agent Security

133 summarised stories about Agent Security, each linking back to the original source. Browse all topics →

+ Follow this topic

Monday, 19 October 2026

Microsoft says AI agents are like insider threats as ‘frontier models can’t be trusted’

TechCrunch 8 hours ago 20

Microsoft introduced Guardian Agents and related protections to monitor and control AI agents used by enterprises. The Guardian Agents feature is part of Project Perception, which debuted in June, and Microsoft also added agent detection that can find up to 60 types of agents. This shifts customers toward running separate oversight systems and adopting Microsoft’s agent security controls instead of relying on AI model providers’ assurances.

Making the internet better for AI agents might make it worse for everyone else

MIT Technology Review 12 hours ago 14 ● 3 sources

Personal AI agents are increasingly being released and used to browse and negotiate on the web, but many websites are blocking them and platforms may redesign the internet around agent traffic. Agentic web traffic tripled from August to September. As a result, customer-facing websites and verification flows could become harder for human browsing while rules evolve over whether agents can access sites and bargain for better deals.

Laplace Intelligence red-teams robots and self-driving cars before they hit the real world

TechCrunch 18 hours ago 22

Laplace Intelligence is developing automated red-teaming for robots and self-driving systems by using high-fidelity simulations plus an AI agent that probes for failure cases before real-world deployment. It will pitch at TechCrunch Disrupt Startup Battlefield 200 on October 13–15, with Applied Intuition’s funding cited as $1.2 billion to date. The approach shifts edge-case testing from human-created scenarios and recorded footage toward AI-generated, interactive corner cases meant to be used by customers, insurers, and regulators.

A hacker broke into John Deere and SharkNinja with an army of AI agents

The Verge 20 hours ago 12 ● 6 sources

A hacker broke into more than 100 websites using an army of mostly self-operating AI agents, according to Norforge. The reported victims included John Deere and SharkNinja, among others. The findings highlight growing risk from AI-powered and escaped AI agents that can automate large-scale breaches, prompting more attention to AI security defenses.

The daily briefing

Every AI story that matters, in your inbox by 8am.

TLDRocket reads all relevant sources, removes duplicate coverage, and summarises the day in two minutes. Follow companies and topics for alerts, or get the briefing in Slack. Free, no spam, unsubscribe anytime.