Google Uncovers Attack Where AI Agents Ran an Entire Credential-Theft Operation With Almost No Human Help
Google Cloud researchers say they've observed attackers hand an autonomous AI agent framework a set of instructions and let it scan, exploit, and harvest more than 23,800 credentials...
AI-Assisted Intruder Reaches Enterprise Root Access in Less Than 10 Hours
An attacker reportedly used frontier models and agentic frameworks to compress a complex enterprise intrusion into less than ten hours. The incident shows how exposed services, embedded secrets...
CrowdStrike Unveils SafeMind Agents to Pit Automated Defense Against AI-Driven Attacks
CrowdStrike has introduced SafeMind, a purpose-built family of offensive and defensive AI models designed around Falcon telemetry and incident-response knowledge. The company says the system can improve detection...
700 Rogue AI Agents Quietly Teamed Up to Breach Hugging Face During a Security Test
During a large-scale OpenAI security evaluation, hundreds of isolated AI agents found a shared cache they weren't supposed to have access to, turned it into a covert message...
Security Leaders Warn the ‘Agentic Attacker’ Has Arrived After AI Models Reportedly Breached Hugging Face on Their Own
An incident in which autonomous OpenAI models allegedly broke out of a sandboxed test environment and gained remote code execution on Hugging Face's infrastructure — carrying out more...
AutoJack: A Single Malicious Web Page Can Hijack Your AI Agent and Execute Arbitrary Code
A critical three-vulnerability exploit chain called AutoJack allows a single malicious web page to hijack Microsoft AutoGen Studio's browsing agent and execute arbitrary code on the developer's machine,...
Five OpenClaw Zero-Days Let Attackers Silently Hijack AI Agent Access on Slack, Teams, and Discord
Researcher Philip Garabandic disclosed five zero-day vulnerabilities in OpenClaw allowing identity spoofing to hijack trusted AI agent access across Slack, Discord, Microsoft Teams, Matrix, and Zalo. The same...
Malicious DeepSeek-Claw AI Skill Delivers Remcos RAT and GhostLoader in Agentic AI Supply Chain Attack
Zscaler ThreatLabZ has uncovered a campaign where attackers published a fake DeepSeek integration for the OpenClaw AI framework on GitHub, hiding malicious commands in a SKILL.md file. The...