AI
LayerX: Anthropic’s Claude Code Can Easily Be Easily Weaponized
LayerX researchers were able to convince the popular AI coding tool to bypass its guardrails and execute malicious instructions.
AI
‘GitLost’ Flaw Lets Attackers Trick GitHub AI Agent Into Leaking Private Repos
Noma researchers again show how easy it is to manipulate AI agents with malicious commands via indirect prompt injection attacks.