Other new ES features include:
- Detection Studio: A unified workspace for detection engineers to plan, develop, test, deploy, and monitor detections. By mapping coverage against the MITRE ATT&CK framework, teams can identify data gaps and validate detection quality in real time. Another new instrument, Malware Threat Reversing Agent, gives customers insight into malware threats, providing summaries and step-by-step breakdowns of malicious scripts.
- Federated Search: Lets SecOps teams gain comprehensive visibility across distributed data sources, according to Cisco.
- Exposure Analytics: Automatically discovers assets and users across the environment. By leveraging data already being ingested, it provides a “Security Truth Layer” without the need for additional agents or tools, Cisco stated.
Cisco DefenseClaw
Cisco is also releasing an open-source secure agent framework called DefenseClaw that lets users define policy-based security, network, and privacy guardrails for Nvidia’s recently released OpenShell and OpenClaw agentic environments.
DefenseClaw scans everything before it runs, according to DJ Sampath, senior vice president of Cisco’s AI software and platform group.
“Every skill, every tool, every plugin, before it’s allowed into your claw environment and every piece of code generated by the claw gets scanned. The scan engine includes five tools: skill-scanner, mcp-scanner, a2a-scanner, CodeGuard static analysis, and an AI bill-of-materials generator. The scan engine includes five tools: skill-scanner, mcp-scanner, a2a-scanner, CodeGuard static analysis, and an AI bill-of-materials generator,” Sampath wrote in a blog post about the news.
DefenseClaw also detects threats at runtime, not just at the gate, Sampath stated. “Claws are self-evolving systems. A skill that was clean on Tuesday can start exfiltrating data on Thursday. DefenseClaw doesn’t assume what passed admission stays safe — a content scanner inspects every message flowing in and out of the agent at the execution loop itself,” Sampath wrote.
And thirdly, DefenseClaw enforces block and allow lists. “When you block a skill, its sandbox permissions are revoked, its files are quarantined, and the agent gets an error if it tries to invoke it. When you block an MCP server, the endpoint is removed from the sandbox network allow-list and OpenShell denies all connections. This happens in under two seconds, no restart required.”
