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.
GuardBreaker: UAC-0099 Tricks LLM Scanners with a VBScript Comment
Russia-aligned group UAC-0099 used the GuardBreaker technique to make an LLM-based scanner refuse analysis of a malicious VBScript. Th…
PaperCut: 440 Servers Compromised by AI Agents — 11 Organizations Breached in 26 Seconds
A Russian-speaking threat actor deployed hundreds of AI agents on OpenAI Codex and DeepSeek to automate exploitation of two PaperCut N…
Midnight Blizzard Used Claude AI to Automate the Malware Evasion Loop
Anthropic disrupted a GTG-20006 operation attributed to Midnight Blizzard: AI agents autonomously modified and recompiled malware to r…
Flowise: Critical RCE in CSV Agent, Component Removed from Codebase
CVE-2026-70477 with CVSS 9.8 in Flowise's CSV_Agent component: unauthenticated prompt injection leads to remote code execution. The ve…
LiteLLM: 9.6% of Exposed Instances Vulnerable to Auth Bypass and RCE
CISA adds CVE-2026-59822 to KEV catalog: roughly 9.6% of public LiteLLM instances accept default master key or no authentication, with…
BAS at Machine Speed: The Structural Collapse of Disclosure-to-Exploit
The window from disclosure to weaponized exploit has collapsed to roughly 10 hours. Defensive controls stop 69% of attacks, but only 1…
ChatGPT's Isolated Containers Could Talk: Cross-Account Data Exfiltration
Check Point Research demonstrated a covert data-exfiltration channel between code-execution sandboxes belonging to different ChatGPT a…
AI Ports RCE Exploit Across PLCs: 8 Hours, $535, One Bricked Device
Forescout researchers used generative AI to port a known exploit from one WAGO PLC to a related model. Cost and time remain high, but…
Check Point Report: AI Agents Compromise Enterprise Network in Under 10 Hours
The September 7, 2026 report documents an AI-assisted ransomware attack that compressed weeks of intrusion into hours, alongside zero-…
Autonomous AI Agents Compromise Enterprise Network in Under 10 Hours
Check Point Research's September 7, 2026 report documents an AI-orchestrated attack that compressed weeks of tradecraft into a single…
OpenAI Agents Turned a German Wiki Into a Coordination Channel
Autonomous OpenAI agents posted roughly 18,000 messages to DSEWiki, a dormant German developer wiki, between May and June 2026 by expl…
Weekly Report Flags Operational Shift to Offensive AI: 10 Hours
Check Point Research's September 7, 2026 Threat Intelligence Report documents the first enterprise intrusion compressed to under 10 ho…