Cisco Open Sources Quarry to Catch AI Agent Attacks Hidden in Harmless Steps
Cisco open sources Project Quarry, a rule language for detecting AI agent attacks.
Cisco has open sourced Project Quarry, a neurosymbolic rule language designed to detect AI agent attacks that unfold across a series of seemingly benign actions. Traditional security tools often fail to identify these threats because they analyze individual actions in isolation. Quarry combines machine learning with rule-based checks to identify suspicious patterns over time, offering a new layer of defense against sophisticated AI-driven attacks.
AI summary of the linked source. Not reviewed by an editor. How this works
Run Cisco?
Get an email when a new story names Cisco, usually within the hour.
Free. Your list stays private and never appears in a subject line. One click stops it. How Vendor Watch worksPrivacy
The lesson from this incident
Full lessonAI-powered agents can execute attacks through sequences of individually harmless actions, each of which passes standard security checks while collectively achieving a malicious goal. Traditional security tools fail here because they evaluate events in isolation rather than tracking behavioral patterns over time. This represents a fundamental blind spot in conventional logging and monitoring stacks, which were not designed for the emergent, multi-step threat model that AI agents enable. Cisco's open-source Quarry project addresses this gap by combining machine learning with rule-based logic to detect suspicious sequences — highlighting how defenders must evolve their monitoring capabilities to match attacker sophistication.
What helps against this
How we list vendors
- Endpoint detection and response (EDR and XDR)
Malware and hands-on-keyboard attackers on laptops and servers get spotted and stopped.
- SOC automation and AI analysts
Alerts arrive faster than the team can investigate them, so real attacks wait in the queue or are closed unread.
- AI application security
Prompt injection, data leaks through AI tools and unapproved AI use get caught.
Indicators of Compromise
Extracted by AI from the linked source. Not reviewed by an editor. How this works
- malware — Claude Code