AI Security and Safety
Agents that can act can also be tricked. This hub covers security and safety for AI systems: prompt injection, what agents are allowed to do and spend, vulnerability research with and against AI, alignment, and the guardrails teams put around production agents.
- 'Your company brain will leak secrets: how we stopped it for big banks - Tanmai Gopal, PromptQL'
- Your Agent Just Authorized What?! - Jay Mok & Ben Coumes, Paypal
- Unlock Agent Autonomy: The Runtime for AI-Native Systems - Tushar Jain, Docker
- Teaching AI to Find Real Vulnerabilities - Prof. David Brumley, Bugcrowd
- You Didn't Ship a Bug. You Just Wrote It for a Human. - Ravi Madabhushi, Scalekit
- Your LLM Deception Monitor Is Broken. The Fix Is in the Training Data - Sachin Kumar, LexisNexis
- Spec-Driven Testing for Agents With A Brain the Size of A Planet — Steven Willmott, SafeIntelligence
- How to Set Up ClawdBot or OpenClaw Securely