The New Stack·1 min·13h agoFREE

On June 17, Tenet Security's Threat Labs team documented a security vulnerability where a public Sentry key could be used to hijack AI agents. This method, referred to as "agentjacking," reportedly allows for the hijacking of systems like Claude Code, Cursor, and Codex. The research highlights how these AI-powered tools could be compromised with access to a seemingly innocuous public key, according to The New Stack.

Developers using Claude Code, Cursor, and Codex face a security risk, as a public Sentry key can reportedly hijack these AI agent systems.