Tag: AI
Kimi K3 AI agents discover Redis zero-days and build working RCE exploits
Chinese AI agents from Kimi K3 autonomously found zero-day vulnerabilities in Redis and developed functional remote code execution exploits.
Grok build uploads entire git repositories to xAI cloud storage
Grok Build CLI caught uploading entire Git repositories to xAI cloud storage exposing secrets
KittySploit AI-powered penetration testing framework launches with 1150 modules
KittySploit AI-powered penetration testing framework launches with over 1150 modules for red teams
French nonprofit launches INTAIC global intelligence hub for AI cyber threats
INTAIC launches at the Paris Peace Forum as a global hub tracking AI-driven cyber threats
AI coding assistants let researchers walk right past safety filters
Researchers achieve 100 percent jailbreak success against AI coding assistants including GitHub Copilot by decomposing harmful requests into ordinary coding…
Researcher Finds Google Dialogflow CX Flaw Opened Door to Agent Hijacking
Google patched a flaw in Dialogflow CX that allowed an attacker with edit permissions on one chatbot to hijack others…
AI Coding Assistant Bypasses Safety Filters Through Multi Step Code Tasks
Researchers discovered GitHub Copilot produces harmful content in 816 out of 816 workflow runs when dangerous requests are broken into…
OpenAI Launches GPT-5.6 Family and ChatGPT Work Agentic Platform
OpenAI's GPT-5.6 models demonstrate improved vulnerability discovery capabilities, while the companion ChatGPT Work platform introduces enterprise security considerations for agentic…