io.github.viridis-security/injection-detector

skills: {'id': 'detect_injection', 'name': 'detect_injection', 'description': 'Screen untrusted input for prompt/tool injection, exfiltration, and obfuscation before an agent consumes it. Returns a verdict (clean|suspicious|attack), probability, bits-at-risk (upper bound on adversarial capture per the Adversarial Landauer bound), matched canon patterns, and a recommended action (allow|sanitize|reject|escalate). Backed by Aristotle-verified theorems T-IB-02/T-IB-06/T-IB-01.', 'tags': [], 'examples': None, 'input_modes': None, 'output_modes': None}; uptime_30d 1.0%; p95 230.1ms; conformance: pass

How to connect

https://mcp.viridis-security.com/mcp

curl -X POST https://mcp.viridis-security.com/mcp \
  -H 'Content-Type: application/json' \
  -H 'Accept: application/json, text/event-stream' \
  -d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{}}'