Red Agents vs. Blue Agents: How to Make AI Better At Defense
The agentic AI playing field was heavily tilted toward offense, so researchers began using red team agents to help teach their blue counterparts.
-
-
Critical Rails Flaw Could Let Unauthenticated Attackers Read Server Files via Image Uploads
Ruby on Rails has released fixes for a critical Active Storage vulnerability that could let unauthenticated attackers read arbitrary files from application servers through crafted image uploads. Tracked as CVE-2026-66066 (CVSS score: 9.5), the flaw can expose the Rails process environment and secrets such as secret_key_base, the Rails master key, database passwords, cloud storage credentials,
-
Who’s Liable When AI Agents Escape? Hugging Face Breach Raises Hard Questions
Dark Reading walks through the many twists and turns in the bizarre story of how OpenAI’s agent AI system broke out of its sandbox and decided to target Hugging Face, and what CISOs should be aware of.
-
Hugging Face Hack Lessons for Cyber Defenders
Dark Reading Confidential Episode 20: Expert Rich Mogull reflects on lessons cyber teams should pull from the OpenAI agent’s attack on Hugging Face.
-
When AppSec Scanners Become a Supply Chain Attack Vector
New research shows how security scanners embedded in the software supply chain can be attacked to serve as a foothold for downstream attacks.
-
Ruflo MCP Flaw Lets Unauthenticated Attackers Run Commands and Poison AI Memory
Cybersecurity researchers have flagged a maximum-severity security flaw in Ruflo, an open-source agent meta-harness for Anthropic Claude Code and OpenAI Codex, that could result in unauthenticated remote code execution. The vulnerability, tracked as CVE-2026-59726 (CVSS score: 10.0), impacts all versions of the project before version 3.16.3. It has been codenamed RufRoot by Noma Security’s
-
Three Critical VMware Flaws Allow Auth Bypass, Code Execution, and VM Escape
Broadcom has released security updates to address multiple security flaws impacting VMware ESX, vCenter, Workstation, and Fusion, three of which have been designated as critical in severity. The first of the three critical-rated flaws is CVE-2026-59309 (CVSS score: 9.8), which has been described as an authentication bypass in VMware vCenter. “A malicious actor with network…
-
Patch-Resistant ‘RufRoot’ Flaw Can Unleash Malicious AI Agent Swarms
The vulnerability in the AI hosting platform Ruflo allows an unauthenticated attacker to take over the system and corrupt memory, so bad behavior can persist after patching.
-
Coordinated Cyberattack Targets 30+ Minnesota Water Systems as One Plant Goes Offline
A coordinated cyberattack targeted operational technology at more than 30 Minnesota community water systems on July 26 and 27, triggering a statewide cybersecurity response. Braham, Plymouth, South St. Paul and Maple Plain have publicly described a plant outage, communications failures or affected automated controls. Braham’s water plant went offline, and the city asked residents to…
-
Nine-Year Fraud Campaign Clones Russian Company Sites to Steal Advance Payments
Cybersecurity researchers have disclosed details of a large-scale fraud campaign that involves creating lookalike websites of major Russian companies with an aim to siphon funds from international firms for more than nine years. According to Russian cybersecurity vendor F6, the threat actors have set up clone websites of Russian companies across fertilizer manufacturers, petrochemical companies