Skip to content
View original post on X: Cisco AI
Published
39/100

Cisco open-sources Project Quarry to detect threats across multi-step AI agent behavior

AICisco introduces Project Quarry, an open-source detection language for identifying threats across multi-step AI agent behavior. The post says individual agent actions may look harmless, while risk emerges when those actions are connected.
Cisco AIVerified on X
@CiscoAI
View on X

An AI agent's actions may look harmless individually. The real risk emerges when they're connected.

Introducing Project Quarry: @Cisco's new open source detection language designed to identify threats across multi-step agent behavior.

See how it works: https://blogs.cisco.com/ai/project-quarry-agent-security-detections

Source details

Cisco AI · x.comPublished · added here

Original title: An AI agent's actions may look harmless individually. The real risk emerges when they're connected.

Topics

AI agentsOpen-source ecosystemSafety & alignmentProduct updates