Enoki
Security testing for AI agents
Enoki tests AI agents for security and safety weaknesses. It attacks your agent the way an adversary would, adapts to how the agent responds, and reports each weakness it finds with the exact attack and the agent's response.
What you can ask
- Test my support agent with Enoki.
Example path → ·
MCP connector
- Server URL
https://mcp.enokilabs.ai/mcp- Login
- OAuth
Tools
Reads data9
Changes data1
Deletes or can't be undone7
Skills
1 in the ChatGPT listing
Have I Been Pwned#426
WorkOS#447