Meta Launches LlamaFirewall Framework to Stop AI Jailbreaks, Injections, and Insecure Code

Meta on Tuesday announced LlamaFirewall, an open-source framework designed to secure artificial intelligence (AI) systems against emerging cyber risks such as prompt injection, jailbreaks, and insecure code, among others.
The framework, the company said, incorporates three guardrails, including PromptGuard 2, Agent Alignment Checks, and CodeShield.
PromptGuard 2 is designed to detect direct