Artificial intelligence security platform DeepKeep has launched a new AI agent attack surface scanning and discovery solution. This tool maps the risks associated with each AI agent within an enterprise workflow.
As organizations increasingly deploy large language model-based agents with access to business applications and data, their attack surface expands in ways traditional cybersecurity controls cannot address. The AI Agent Scanner provides immediate visibility into what AI agents can access, their interactions with tools and data, and potential vulnerabilities.
The solution performs robust attack surface scanning to map an agent’s entire threat landscape, identifying connected tools, their intents, data sources, and vulnerabilities. It generates a visual risk map offering vital insights to help businesses understand their agent's exposure and threats, indicating how elements may be leveraged by attackers and what defensive actions are needed.
"AI agents are no longer operating in isolation; they’re quickly becoming fundamental parts of entire business workflows," explains Yossi Altevet, co-founder and chief technology officer of DeepKeep. "But without proper safeguards, their expanding attack surface will rapidly become a massive enterprise liability."
DeepKeep’s solution also provides runtime protection for select agentic frameworks. It identifies where AI firewalls and guardrails should be placed based on observed agent behavior, tool access, and data exposure, allowing security teams to actively reduce risk during execution.
The platform currently supports frameworks including Microsoft, Agentforce, OpenAI Agents, CrewAI, Amazon Bedrock AgentCore, n8n, and Make. DeepKeep plans to expand its AI agent security capabilities across the full AI lifecycle in 2026.