MITRE ATLAS · Execution
AML.T0103 · Deploy AI Agent
Adversaries may launch AI agents in the victim's environment to execute actions on their behalf. AI agents may have access to a wide range of tools and data sources, as well as permissions to access and interact with other services and systems in the victim's environment. The adversary may leverage these capabilities to carry out their operations.
Mitigations
- Code Signing
Related techniques
- ASI10 Rogue Agents OWASP Agentic
In the news
-
Attackers' AI Agents Found a Zero-Day in Medical-Imaging Software and Gained Root Access
Amazon Threat Intelligence says suspected China-linked hackers used autonomous AI agents to find a zero-day in MONAI Label and gain root on a university server.
PatchUpgrade MONAI Label beyond 0.8.5 or restrict access to the server
-
Chinese state group developing automated attack tool for cyber espionage, Google says
Google reports threat actors, including a Chinese state group, are building autonomous multi-agent offensive AI frameworks for multi-stage cyber espionage intrusions.
ReviewReview exposure to autonomous AI-driven intrusion activity and monitor for named offensive frameworks
-
Google warns that fully automated cyberattacks have arrived and will get worse fast
Google GTIG says it observed an AI framework called exploit_agent, found on an exposed server, autonomously finding, patch-diffing, building and running exploits.
HuntHunt for exploit_agent artifacts on internet-facing servers
-
China-Nexus Actors Breach 10 Organizations in AI-Driven Attacks
China-nexus actors breached 10 organizations in autonomous AI-driven attacks against manufacturing, defense, and civil rights groups, using the Cairn framework.
ReviewReview exposure of manufacturing and defense assets to autonomous AI-driven intrusion
-
Google Finds Hackers Using AI Agents to Build and Run Exploits From Software Patches
Google reports threat actors are using autonomous multi-agent offensive frameworks such as ARTEX, CAIRN, CyberStrikeAI, and PentAGI to run multi-stage intrusions.
PatchApply the mitigations or fixed version described in the BerriAI advisory GHSA-wxxx-gvqv-xp7p.
CVEs
Mappings are AI-assisted and checked against the framework definitions; corrections welcome.