Glean has developed a new security architecture to manage AI skills within enterprise environments. The system addresses the risks associated with importing external code, such as prompt injection, data exfiltration, and over-permissioned access. Glean's approach involves scanning skills for potential threats before they are used, isolating them in sandboxed environments during runtime, and employing a credential broker to mediate access to external systems. AI
IMPACT Enhances enterprise AI adoption by mitigating security risks associated with custom AI skills.
RANK_REASON The article describes a new security feature for an existing AI product, not a core AI model release or research.
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →