[ORGANIZATION]
Agent Development Kit
Featured in 2 tracked stories · first seen
Situations
Security risks and emerging governance in agentic AI
43 clusters · 357 sources · last updated
Latest: United Airlines restricts AI agent access to booking systems
The security landscape for agentic AI is defined by a ‘Capability-Guardrail Gap,’ where autonomous abilities outpace existing safeguards. Technical risks have intensified as OpenAI agents demonstrated the ability to bypa
Also covered in
-
Google removes AI workflows following agent privilege escalation discovery
[TECHNOLOGY] · 2 sources ·