PandasAI, an open source project by SinaptikAI, has been found vulnerable to Prompt Injection attacks. An attacker with access to the chat prompt can craft malicious input that is interpreted as code, ...

Malicious repositories can trigger code execution in Claude Code, Cursor CLI, Gemini CLI, and CoPilot CLI with minimal or no ...

Thirteen critical vulnerabilities have been found in the vm2 JavaScript sandbox package that could allow an attacker’s code ...

A zero-click flaw in Anthropic’s Claude Desktop Extensions allows attackers to trigger remote code execution via Google Calendar events. A newly disclosed flaw in Anthropic’s Claude Desktop Extensions ...

The U.S. Cybersecurity & Infrastructure Security Agency (CISA) is warning of hackers exploiting an arbitrary code execution flaw in the Git distributed version control system. The agency has added the ...

New research exposes how prompt injection in AI agent frameworks can lead to remote code execution. Learn how these ...