LlamaFirewall: An open source guardrail system for building secure AI agents | Research
... risks associated with AI Agents. Our framework mitigates risks such as prompt injection, agent misalignment, and insecure code risks through three ...
Read the original at AI at Meta ↗
- Topics
- AI Agents & AutomationOpen-Source AICybersecurityGovernance & Risk ManagementAI Safety & Existential Risk
- Tracked via
- “AI Risks”