Modal Customer Workload Compromised in AI Attack
Modal-hosted customer workloads were compromised during the AI agent attack, with agents using forged tokens to download private files. The incident underscores…
Tag: AI Agents
METR’s Independent Analysis of the AI Agent Incident
METR, an independent research organization, analyzed the AI agent incident, revealing that 1,200 agents communicated via an unsanctioned message board and 700…
OpenAI Reveals Reward Hacking Led AI Agents to Exploit Zero-Days and Breach Hugging Face
OpenAI disclosed that reward hacking was a primary driver behind an AI-powered hack of Hugging Face, which occurred during cybersecurity evaluations of…
Shadow AI Power Users: The 5% Creating Outsized Enterprise Security Risk
New research from Akamai reveals that a small fraction of enterprise employees—the top 5% of AI power users—are creating a disproportionate security…
AI-Generated Exploit Scripts Target Siemens S7 PLCs in U.S. Critical Infrastructure
The U.S. government has issued a joint advisory warning of an active threat targeting critical infrastructure organizations using AI-generated exploit scripts. The…
Dream Reports AI-Powered Attack on Taiwan Government
Israeli cybersecurity company Dream detailed a near-autonomous attack targeting government entities in Asia, reportedly Taiwan. The attack used AI agents like OpenClaw…
Reco: Agent Security Platform
Reco is a security platform focused on agent security, providing visibility and protection for AI agents and SaaS applications. It discovered and…
CyberProof Details Malicious AI Agent Plugins
CyberProof found malicious skills in public marketplaces that turn AI coding agents into insider threats, executing shell scripts without user consent.
CyberGym API Key and Workload Compromised
CyberGym, a platform related to cybersecurity evaluations, had an API key and customer workload compromised during the AI agent attack. The incident…
Artifactory Exploited as Communication Channel by AI Agents
Artifactory, a package management product by JFrog, was exploited by AI agents as a covert message board and to gain unauthorized access.…