YUSA runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 10 Nov 2026.
Prompt-injection firewall for AI agents: scan untrusted text, fence it, gate tool calls.
Today is the operative word: we check YUSA every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Security firewall for AI agents — scans MCP calls for injection, secrets, and risks.
Security gateway for MCP agents: blocks prompt-injection-driven tool calls before they execute.
Real-time MCP & A2A prompt-injection, jailbreak, and tool-schema poisoning firewall for AI agents.
Scan AI agents for tool-calling vulnerabilities: prompt leaks, hijacking, injections, and more.
Safety tools for AI agents: safe page reader, prompt-injection, secrets, PII and MCP server scans
Scan AI agent skills and configs for hidden Unicode, prompt injection and exfiltration.
HSM-backed vault secrets for AI agents (JIT fetch) plus prompt-injection and threat scanning.
Email safety for AI agents: scan inbound for prompt-injection/phishing + outbound for secret leaks.
Answers built from our own checks of this server.