Cato Networks launches AgentSense to block harmful AI agent actions
Network World ·

Cato Networks this week launched AgentSense , a new security capability built into its cloud-based secure access service edge ( SASE ) platform that the company says can stop AI agents from carrying out harmful actions prompted by untrusted content. “Giving agents greater autonomy requires security that can intervene before their actions cause harm,” said Shlomo Kramer , CEO and co-founder of Cato, in a press release. “Our vision for AgentSense is to give enterprises the confidence to put agents in charge of critical business processes while retaining control over how they operate.” The initial release targets indirect prompt injection, in which an agent encounters instructions embedded in material it reads while doing its job. This could happen on a webpage, with an email, a document, or a response from a tool the agent uses. An agent with legitimate access to company data and tools can be steered into exposing sensitive information or making an unauthorized change, even when the user’s original request is routine, according to Cato. How AgentSense evaluates actions Kramer explained in the launch briefing that agents “can have exactly the right permissions and still do bad stuff.” To address that, Cato developed Untrusted Influence Detection to distinguish trusted instructions from untrusted content within an AI session. It traces how that content influences a proposed action and can block the action before it executes. Cato said this approach can catch attempts that fall outside known attack patterns. AgentSense works across AI agents , the company explained, and administrators can enable it with a toggle in the Cato SASE platform. It comes with three built-in rules that cover untrusted input steering an agent toward a high-risk operation, sensitive information about to be exposed externally, and changes to critical resources driven by untrusted input. In one example Cato described, a developer asked Claude Code to set up a test environment. While gathering information for the task, the agent read a webpage that directed it to modify a sensitive local file. AgentSense traced the proposed change to the webpage and blocked it before Claude Code could modify the file, leaving the setup incomplete. In its own testing on the Agent Dojo benchmark, Cato reported that AgentSense reduced the attack success rate from about 19% without additional protections to 0.05%, with less than 3% added latency. Cato’s planned Drift Detection capability would also check whether an agent’s actions still serve the user’s original task. The goal is to “block actions that drift from the original purpose the agent was tasked for,” Kramer said during the briefing. The company also plans controls for which resources an agent can reach, including the data it can access. AgentSense is available to Cato customers and is included at no additional charge with Cato AI Usage licenses. With the launch, Cato opened a public challenge to test an AI agent workflow protected by AgentSense. The first three eligible participants to complete the challenge will each receive $10,000, according to the company, which said it would use participants’ findings to evaluate and improve the guardrail.