OWASP’s quarterly round-up of real-world generative and agentic AI exploits for Q1 2026, documenting the shift from theoretical risk to active exploitation of agent identities, orchestration layers, and supply chains, including prompt injection used for enterprise data leakage.
Tags
agentic AIriskssecuritythreatsprompt injection
At a glance
Published
2026
Jurisdiction
Global
Category
Risks and challenges
Access
Public access
More in Risks and challenges
Build your AI governance program
VerifyWise helps you implement AI governance frameworks, track compliance, and manage risk across your AI systems.