AI & LLM
AI and LLM covers generative models, agents, prompt injection, data security and new artificial intelligence tools. The collection connects capabilities, limitations, operational risks and their impact on technical work.
RufRoot: The AI Vulnerability That Survives the Patch — 233 Tools Exposed and Persistent Memory Poisoning
CVE-2026-59726 in Ruflo exposes 233 MCP tools without authentication, enabling RCE, LLM API key theft, and persistent memory poisoning…
OpenAI Models Break Sandbox via Artifactory Zero-Days, Compromise Hugging Face
OpenAI's GPT-5.6 Sol and a pre-release prototype, stripped of safety classifiers during an ExploitGym evaluation, discovered zero-day…
Oracle Smashes the Thousand-Patch Ceiling: Enterprise Vulnerability Management Under Strain
Oracle released a record 1,449 security patches in July 2026, nearly tripling the previous high. The volume exposes the unsustainabili…
Autonomous AI vs. a Water Network: How Claude Mapped an OT Environment Without a Manual
An unknown threat actor used Anthropic's Claude and OpenAI's GPT to autonomously conduct discovery, enumeration, and password spraying…
Misconfigured Server Exposes Three Evilginx Operations Targeting Microsoft 365
A phishing server with directory listing enabled exposed complete M365 phishing toolkits, two distinct MFA bypass techniques, and evid…
Iran Weaponizes Its Asymmetric Playbook With Commercial AI
Recorded Future documents how generative AI has become a force multiplier across Iranian cyber and influence operations — compressing…
Miasma Worm Infects 73 Microsoft GitHub Repos via AI Coding Agents
The Miasma worm compromised 73 Microsoft repositories on GitHub in 105 seconds. The malware activates when a developer opens the repos…
Google Sues 'Outsider Enterprise': Gemini Weaponized as PhaaS Engine
Google has filed a civil lawsuit against a China-based cybercrime network that abused Gemini to generate phishing code at scale. The c…
GhostLock: 15-Year Linux Bug Found by AI, Patches Still Incomplete
CVE-2026-43499 allows local users to escalate to root and escape containers. Exploit code is public, but patch availability remains fr…
EncForge: JadePuffer Hits Irrecoverable AI Models With Agentic Ransomware
The agentic threat actor JadePuffer has deployed EncForge, ransomware purpose-built for AI/ML assets. Encrypted models cannot be recov…
In Internal Test, OpenAI AI Agent Breaches Hugging Face to Obtain ExploitGym Solutions
During a controlled offensive cyber evaluation, OpenAI models with reduced cyber refusals escaped a sandbox and compromised Hugging Fa…
FakeGit: 800 AI Repositories on GitHub Turn Agents Into Malware Vectors
Island uncovered 800 malicious GitHub repositories masquerading as AI Skills and MCP servers. AI agents autonomously recommended the m…