MEDIUMAi
Global

The Model Is the Malware | What Four Agentic Intrusions Tell Defenders

·Source: SentinelLabs

Updated:

Executive Summary

OpenAI, Anthropic and Meta disclosed agents reaching external systems. The tools didn't matter, and that changes the playbook for investigating intrusions.

Analysis

OpenAI, Anthropic and Meta disclosed agents reaching external systems. The tools didn't matter, and that changes the playbook for investigating intrusions.
Source Attribution

Originally published by SentinelLabs on Aug 13, 2026.

Related Threats

MEDIUMAiNEW

Westpac to reshape software engineering with Amp Frontier Corporation

Westpac has contracted with San Franciscop-based Amp Frontier Corporation to build a suite of AI agents for software engineering tasks.

Finextra
MEDIUMAi

Perplexity Builds Guardrails to Rein in Rogue AI Agents

<img src="https://ismg-cdn.nyc3.cdn.digitaloceanspaces.com/articles/perplexity-builds-guardrails-to-rein-in-rogue-ai-agents-image_small-9-a-32596.jpg" align=right hspace=4><b>Open-Source Numbat Blocks Agent Actions That Violate Enterprise Security Policies</b><br>Perplexity designed its open-source tool Numbat tool to detect and block AI agents from stepping outside enterprise safety policies. The

Bank Info Security
LOWAi

Fortinet Buys Virtue AI for Agent and Model Runtime Controls

<img src="https://ismg-cdn.nyc3.cdn.digitaloceanspaces.com/articles/fortinet-buys-virtue-ai-for-agent-model-runtime-controls-image_small-8-a-32592.jpg" align=right hspace=4><b>Acquisition Adds Offensive and Defensive Testing for Agents and Models</b><br>Fortinet acquired Virtue AI's technology to extend FortiAIGate with red- and blue-team testing, runtime controls and policy enforcement for AI age

Bank Info Security