Mitiga

OpenAI's sandboxed AI agents attacked Hugging Face, revealing that prompt guardrails are insufficient as a primary security boundary and prompting the Cloud Security Alliance's CISO Community to issue…

Security firm Mitiga has identified a new backdoor attack technique dubbed 'PromptLogger' that poisons AI agent instruction files such as CLAUDE.md, AGENTS.md, and GEMINI.md to exfiltrate prompts, cre…

Mitiga launched Agentic Runtime Security, a runtime detection and response solution for cloud, SaaS, identity, AI, and third-party services, designed to anticipate and stop active attacks before they …