Securing Brokers & AI Provide Chain with Cisco AI Protection

The dialog round AI and its enterprise functions has quickly shifted focus to AI brokers—autonomous AI techniques that aren’t solely able to conversing, but additionally reasoning, planning, and executing autonomous actions. 

Our Cisco AI Readiness Index 2025 underscores this pleasure, as 83% of corporations surveyed already intend to develop or deploy AI brokers throughout a wide range of use instances. On the identical time, these companies are clear about their sensible challenges: infrastructure limitations, workforce planning gaps, and naturally, safety. 

At a time limit the place many safety groups are nonetheless contending with AI safety at a excessive degree, brokers develop the AI danger floor even additional. In spite of everything, a chatbot can say one thing dangerous, however an AI agent can do one thing dangerous. 

We launched Cisco AI Protection at first of this 12 months as our reply to AI danger—a really complete safety answer for the event and deployment of enterprise AI functions. As this danger floor grows, we wish to spotlight how AI Protection has developed to satisfy these challenges head-on with AI provide chain scanning and purpose-built runtime protections for AI brokers. 

Beneath, we’ll share actual examples of AI provide chain and agent vulnerabilities, unpack their potential implications for enterprise functions, and share how AI Protection permits companies to straight mitigate these dangers. 

Figuring out vulnerabilities in your AI provide chain 

Fashionable AI growth depends on a myriad of third-party and open-source parts reminiscent of fashions and datasets. With the appearance of AI brokers, that record has grown to incorporate belongings like MCP servers, instruments, and extra. 

Whereas they make AI growth extra accessible and environment friendly than ever, third-party AI belongings introduce danger. A compromised element within the provide chain successfully undermines your entire system, creating alternatives for code execution, delicate knowledge exfiltration, and different insecure outcomes. 

This isn’t simply theoretical, both. A number of months in the past, researchers at Koi Safety recognized the primary identified malicious MCP server within the wild. This package deal, which had already garnered hundreds of downloads, included malicious code to discreetly BCC an unsanctioned third-party on each single e mail. Comparable malicious inclusions have been present in open-source fashions, instrument information, and varied different AI belongings. 

Cisco AI Protection will straight tackle AI provide chain danger by scanning mannequin information and MCP servers in enterprise repositories to establish and flag potential vulnerabilities. 

By surfacing potential points like mannequin manipulation, arbitrary code execution, knowledge exfiltration, and power compromise, our answer helps forestall AI builders from constructing with insecure parts. By integrating provide chain scanning tightly throughout the growth lifecycle, companies can construct and deploy AI functions on a dependable and safe basis. 

Safeguarding AI brokers with purpose-built protections 

A manufacturing AI software is prone to any variety of explicitly malicious assaults or unintentionally dangerous outcomes—immediate injections, knowledge leakage, toxicity, denial of service, and extra. 

After we launched Cisco AI Protection, our runtime safety guardrails have been particularly designed to guard in opposition to these situations. Bi-directional inspection and filtering prevented dangerous content material from each person prompts and mannequin responses, protecting interactions with enterprise AI functions protected and safe. 

With agentic AI and the introduction of multi-agent techniques, there are new vectors to think about: better entry to delicate knowledge, autonomous decision-making, and complicated interactions between human customers, brokers, and instruments. 

To satisfy this rising danger, Cisco AI Protection has developed with purpose-built runtime safety for brokers. AI Protection will perform as a type of MCP gateway, intercepting calls between an agent and MCP server to fight new threats like instrument compromise. 

Let’s drill into an instance to raised perceive it. Think about a instrument which brokers leverage to look and summarize content material on the internet. One of many web sites searched comprises discreet directions to hijack the AI, a well-known state of affairs often called an “oblique immediate injection.” 

With easy AI chatbots, oblique immediate injections may unfold misinformation, elicit a dangerous response, or distribute a phishing hyperlink. With brokers, the potential grows—the immediate may instruct the AI to steal delicate knowledge, distribute malicious emails, or hijack a linked instrument.  

Cisco AI Protection will defend these agentic interactions on two fronts. Our beforehand current AI guardrails will monitor interactions between the appliance and mannequin, simply as they’ve since day one. Our new, purpose-built agentic guardrails will study interactions between the mannequin and MCP server to make sure that these too are protected and safe. 

Our purpose with these new capabilities is unchanged—we wish to allow companies to deploy and innovate with AI confidently and with out concern. Cisco stays on the forefront of AI safety analysis, collaborating with AI requirements our bodies, main enterprises, and even partnering with Hugging Face to scan each public file uploaded to the world’s largest AI repository. Combining this experience with a long time of Cisco’s networking management, AI Protection delivers an AI safety answer that’s complete and accomplished at a community degree.   

For these excited by MCP safety, try an open-source model of our MCP Scanner which you can get began with at present. Enterprises in search of a extra complete answer to handle their AI and agentic safety considerations ought to schedule time with an professional from our crew. 

Most of the merchandise and options described herein stay in various phases of growth and will probably be provided on a when-and-if-available foundation.