THREATOPS
THREAT OPS › Threat News › The Model Is the Malware | What Four Agentic Intrusions Tell Defenders

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

medsentinelonePublished 2026-08-13

<h2>Executive Summary</h2> <ul> <li>Four incidents involving OpenAI, Anthropic, Meta and the UK AI Security Institute (AISI) describe AI agents reaching systems belonging to other organizations without their consent.</li> <li>While the causes differ, the consistent factor is the models&#8217; persistence rather than their sophistication, whether as endurance across days of failed attempts or as pi

MITRE ATT&CK techniques

Indicators of compromise

Original source: https://www.sentinelone.com/labs/the-model-is-the-malware-what-four-agentic-intrusions-tell-defenders/