← back
AI + Security & Safety — Don Bosco Durai
Original: AI + Security & Safety — Don Bosco Durai
Takeaway
Single-process agent frameworks violate zero-trust — credentials, prompts, and tool outputs need isolation boundaries to prevent injection-based privilege escalation.
Summary
- Private AI's open-source safety/security framework for GenAI agents addresses the 'zero-trust gap': most agent frameworks run agents/tasks/tools in one process sharing service-admin credentials.
- Risks: prompt-injected tools can read other tools' credentials, third-party libs can sniff prompts, agent non-determinism creates unknown-unknown attack surface.
- Maps the agent topology (agents → tasks → tools → APIs/DBs → memories) and proposes process-level isolation and credential scoping per tool call.
- Author also created Apache Ranger (used by AWS, GCP, Azure for big-data governance).
securityagentssafety
Original description
Multi-agent systems are revolutionizing industries, driving innovation with autonomous agents that collaborate in dynamic environments. But with great complexity comes great vulnerability. If you’ve ever worried about adversarial behaviors, privacy breaches, or data leakages in these systems, you’re not alone. These threats can erode trust and jeopardize the integrity of even the most cutting-edge applications. What if there were ways to safeguard these systems without stifling innovation? Enter a balanced approach that combines robust security frameworks with adaptive, innovation-friendly strategies. In this talk, we’ll explore how to identify and mitigate the unique risks inherent in multi-agent systems while fostering an environment where creativity thrives. Learn practical techniques for maintaining security, ensuring safety, and enabling innovation in these transformative systems. Recorded live at the Leadership Track Session Day from the AI Engineer Summit 2025 in New York. Learn more at https://ai.engineer and purchase tickets to our next event, the AI Engineer World's Fair, in SF June 3 - 5 here: https://ti.to/software-3/ai-engineer-worlds-fair-2025 About Bosco Bosco is an entrepreneur and thought leader in enterprise security, known for his work in Security, Compliance, and Governance. He co-created Apache Ranger, an open-source project widely considered the gold standard in Big Data security. Currently, as the CTO and co-founder of Privacera, Bosco is leading the effort to open-source PAIG.ai, a project dedicated to security, safety, and governance for Generative AI applications and AI Agents.