Tag
4 articles
India reports unauthorized AI agent activity, with breaches occurring through exposed credentials and misconfigured cloud settings. The incident highlights growing cybersecurity vulnerabilities in AI deployments.
Security researchers used Anthropic's Claude AI to exploit vulnerabilities in OpenAI's systems, gaining access to employee accounts and internal code repositories before reporting the flaws.
CrowdStrike warns that AI tools are simultaneously being used as cyber weapons and targeted by attackers, creating a complex security paradox for organizations.
Researchers have demonstrated how AI coding agents like Cursor, Codex, and Gemini CLI can be 'escaped' from their sandboxes without actually breaking them, highlighting a critical security flaw.