Wiz opens public preview of AI Security Agent
Understand this story
Wiz released AI Security Agent and opened a public preview through Wiz Preview Hub. The agent can automatically inventory custom AI applications, models, system prompts, MCP servers, and tool definitions across self-hosted environments, supported PaaS platforms, and code repositories, and correlate application-layer analysis with cloud context to reconstruct end-to-end attack paths. Wiz states that in multiple customer environments, the agent detected up to 5 times as many AI agents as traditional discovery engines.
AI overview based on source reports · Updated 1 days ago
Coverage timeline
Follow the coverage to explore different perspectives.
- Wiz ResearchIntroducing the Wiz AI Security Agent
Wiz announced the Wiz AI Security Agent in Public Preview, which analyzes AI application code, prompts, and configurations across self-hosted environments, supported PaaS platforms, and code repositories to inventory agents, models, prompts, MCP servers, and tools. It compares each agent's intended purpose against its actual capabilities and permissions, then feeds findings into the Wiz Security Graph to correlate AI-native risks with cloud exposure, identities, permissions, and sensitive data. Wiz says the agent has detected up to five times as many AI agents as traditional discovery engines in customer environments.
Activity for this story
- Current comparable activity
- 4
- Peak comparable activity
- 10Nov 17 03:00
- Change in the past 24 hours
- -49%
Trends compare the same fully observed participants, which may cover fewer participants than current activity. Move the pointer or tap the chart to inspect hourly activity; use the left and right arrow keys with a keyboard.