Yuhina

A security triage agent that learns from its own mistakes. When it gets a severity call wrong, Phoenix MCP turns the miss into a regression test and a better prompt — automatically.

ADKGemini 3 FlashPhoenix MCPRepair MCPCloud Run
0%
Round 1
CVSS-only
100%
Round 2
After self-improve

5 real CVE alerts · One self-improve loop · Zero manual rules

How it works

One button. The agent runs 5 CVE alerts, discovers its mistakes, improves its own prompt through Phoenix MCP, then reruns. No human rules needed.

Note: The full loop runs 3 subprocess rounds on Cloud Run with Phoenix MCP sidecars. Expect 5–10 minutes total.

Try it yourself

Send any security alert to the improved agent. It consults the project module graph, checks exposure paths, and returns a triage decision with evidence.