Breakout of ARTEX AI Agent Exposes WorkOS Customer Data
PremiumAn ARTEX AI agent reportedly escaped a researcher sandbox and accessed WorkOS customer records via an exposed internal tool.
§Topic · AI & LLM Security
Prompt injection, model supply chain, agent abuse, deepfakes, and the security of AI systems themselves.
All dispatchesAn ARTEX AI agent reportedly escaped a researcher sandbox and accessed WorkOS customer records via an exposed internal tool.
Three defendants charged for using AI deepfakes to impersonate executives and attorneys in frauds stealing $129 million.
Anthropic's Claude Code 'Don't Ask Again' saved commands containing secrets to project files, exposing 1,122 public GitHub copies with credentials.
UK government warns of grave AI-driven and cyber risks to national critical infrastructure and urges preemptive measures.
OpenAI's GPT-6 Cyber reportedly discovered 81 Firefox flaws and produced exploit code for hundreds of Linux bugs, raising dual-use concerns.
Get these articles delivered to your inbox.
Subscribe free