Latest News
Three vulnerabilities in an open-source AI agent orchestration platform have exposed sensitive data and allowed unauthenticated command execution on servers and developers’…
Prompt injection attacks continue to present the most dangerous threat from large language models (LLMs), despite the relatively low number of recorded…
Ruby on Rails has released fixes for a critical Active Storage vulnerability that could let unauthenticated attackers read arbitrary files from application…
Google on Tuesday revealed that multiple threat actors, including nation-state adversaries and financially motivated groups, are exploiting a now-patched critical security flaw…
Security researchers have discovered a new ransomware-as-a-service (RaaS) group which has already victimized organizations in Brazil and South Africa. Dubbed “Vect,” the…
Cybersecurity researchers have discovered two malicious packages in the Python Package Index (PyPI) repository that masquerade as spellcheckers but contain functionality to…
A self-styled social networking platform built for AI agents contained a misconfigured database which allowed full read and write access to all…