AI Agent Exploits Exposed Models in Autonomous Cyber Attacks

Symantec's Threat Hunter Team identified an AI attack agent in the wild that autonomously scans the internet for vulnerable endpoints and exploits them without human intervention, running unattended for up to 100,000 steps. The tool was built using off-the-shelf jailbreak and exploitation techniques, according to Symantec's Threat Hunter Team.

Symantec's Threat Hunter Team caught a sophisticated AI attack agent in the wild, designed to autonomously scan the internet for vulnerable endpoints and exploit them without human intervention. This autonomous tool was built using off-the-shelf jailbreak and exploitation techniques, and could run unattended for up to 100,000 steps.