Map / AI Red Teaming / Enoki Labs
Enoki Labs
enokilabs.ai ↗ · LinkedIn ↗ · Open on the map
Capabilities
Security and safety testing for AI agents, and security testing for MCP servers. Enoki attacks the deployed agent the way an adversary would, shows the exact attack and the agent's response behind every finding, and re-runs the attack to confirm a fix holds.
Sensors / integration
Adaptive, multi-turn attacks against the agent's endpoint, including through content the agent reads (indirect prompt injection). No code changes, SDK or install. Runs from the dashboard, from a coding agent over MCP, or from CI/CD over the REST API.
Protections
Findings mapped to the OWASP Top 10 for LLM Applications, the OWASP Top 10 for Agentic Applications and MITRE ATLAS, each with severity and the reproducing attack. Fixed findings are re-tested on every release. It is a testing platform, not a runtime guardrail, and does not monitor production traffic.
Differentiator
Tests the whole deployed agent, including the tools it calls, data it reads and permissions it holds, not only the model, and ties every finding to an attack you can re-run after a fix. Based in Ghent, Belgium (operated by EthicGate BV); backed by RDY.VC, Fortino Ventures and Datadog.
Team & funding
- Founders
- Sander Noels, Joachim Roelants
- Investors
- RDY.VC, Fortino Ventures, Datadog
Other AI Red Teaming companies
A Security · AccuKnox · ActaClad · ActiveFence · Advai · Adversa AI · Aether AI · AgentFox · Aikido · AIM Intelligence · Akto · Alice · See all →
Last updated · Get the “Listed on” badge