DeepKeep Launches AI Agent Attack Surface Mapping and Discovery Solution

TEL AVIV, Israel, March 3, 2026 -DeepKeep, the end-to-end AI security platform, today launched an AI agent attack surface scanning and discovery solution, mapping the risks associated with each agent within an agentic enterprise workflow. AI agents are predicted to make at least 15% of routine business decisions by 2028, expanding the enterprise attack surface in ways traditional cybersecurity controls weren't designed to address.

The AI Agent Scanner performs attack surface scanning to map an agent's entire threat landscape, identifying connected tools, data sources, and vulnerabilities according to the OWASP Top 10 for Agentic Applications, and provides runtime protection for select agentic frameworks.

"AI agents are no longer operating in isolation; they're quickly becoming fundamental parts of entire business workflows. But without proper safeguards, their expanding attack surface will rapidly become a massive enterprise liability," said Yossi Altevet, CTO and Co-Founder of DeepKeep.

The solution currently supports leading agentic frameworks, including Microsoft-based frameworks, Agentforce, OpenAI Agents, CrewAI, Amazon Bedrock AgentCore, n8n, and Make.