Leaks through Claude Code and other missed incidents
Our Compromise Assessment service report features such a hidden threat as generative AI
LLM
LLM for pentesting: speed isn't everything
We found out which local LLMs are better at finding vulnerabilities
Pentesting by AI: Local LLMs Benchmark
Comparative analysis of multiple LLMs in their ability to uncover vulnerabilities
Yes, we can RCE via your AI agent OpenClaw
Overly autonomous LLM executes commands not requested by the user