Cisco announced a sweeping evolution of its security portfolio to help enterprises adopt agentic AI with confidence, combining agent protection, interaction governance, and resilient connectivity for AI-driven workflows.
As organizations move from AI assistants to autonomous agents that use tools and data across hybrid environments, security teams need to strengthen agentic defenses, govern agent interactions with enterprise systems and external services, and maintain reliable, cryptographically protected connectivity at scale.
“In the age of AI, safety and security are pre-requisites for adoption, and AI agents bring a whole new set of challenges,” said Jeetu Patel, Cisco’s President and Chief Product Officer. “As agents take on critical enterprise roles, we’re developing protections that work both ways: preventing agents from being compromised and controlling what they can access and do on our behalf.”
Protect agents from compromise, manipulation, and poisoned tooling
Agentic AI innovations have expanded the attack surface across AI supply chains and the tool ecosystem. Enterprises need protections that reduce the risk of agents being manipulated, or hijacked, including during tool interactions.
Also Read: Criminal IP Integrates with IBM QRadar to Deliver Real-Time Threat Intelligence Across SIEM and SOAR
In the biggest expansion since its January 2025 launch, Cisco AI Defense delivers new features to better secure agents and the AI supply chain. These features include:
- AI BOM (Bill of Materials): Provides centralized visibility and governance for AI software assets, including model context protocol (MCP) servers and third-party dependencies, to secure the AI supply chain
- MCP Catalog: Discovers, inventories, and helps manage risk across MCP servers and registries spanning public and private platforms, strengthening AI governance
- Advanced algorithmic red teaming: Expands the scope of AI security assessments with adaptive single and multi-turn testing for models and agents in multiple languages
- Real-time agentic guardrails to keep agents and applications safe: Continuously monitor and inspect agentic interactions to detect manipulation or unsafe behavior—such as poisoned tools or prompts designed to trigger unauthorized tool use—helping teams enforce policy and reduce compromise risk
Together, these updates help teams inventory and govern AI assets, understand provenance, and surface vulnerabilities earlier in the AI development lifecycle.
Since launch, AI Defense has mapped to leading AI frameworks from organizations like NIST, OWASP, and MITRE. The latest updates add mapping to Cisco’s new Integrated AI Security and Safety Framework to help teams better understand adversary objectives and measure risk exposure.
In addition, AI Defense’s runtime protections now feature a developer-ready integration with NVIDIA NeMo Guardrails’ open source framework, offering organizations a modular, interoperable architecture to protect AI systems in real time in production. AI Defense is a key component of the Cisco Secure AI Factory with NVIDIA, a validated reference architecture to securely power AI workloads in customer environments.
“AI security teams are now being asked three questions at once: what AI assets do we have, where did they come from, and how will they behave in production as agents interact with tools and third-party services,” said Chirag Mehta, Vice President and Principal Analyst at Constellation Research. “With AI BOM and MCP governance plus multi-turn red teaming and real-time guardrails, Cisco AI Defense is targeting the full risk path from the AI supply chain to agentic runtime.”
SOURCE: Cisco