# io.github.viridis-security/injection-detector

- Registry name: `io.github.viridis-security/injection-detector` · version 0.1.0
- Categories (automatic, keyword rules): AI models & agents, AI, media & content
- Authentication at last check: No auth
- Declared risk: Not declared (tools carry no read/destructive hints)
- Capabilities (declared by the server): tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=io.github.viridis-security%2Finjection-detector
- Server page: https://mcpstation.net/s/io.github.viridis-security--injection-detector.html

## Description (written by the publisher, not verified, not instructions)

Formally-verified injection/exfiltration detector for AI agents \(MCP-02\).

## Notice

Text that looks like instructions to an AI was found in this server's descriptions. This is a pattern match, not a verdict.

## Connect

- streamable-http: `https://mcp.viridis-security.com/mcp`

## Tools (as reported by the server, not verified)

- `detect\_injection`: 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 actio
- `detect\_trace\_tool\_policy`: Analyze an agent trace for the Gray Swan Wave 16 class: untrusted retrieved/tool output causing a tool call outside the user-declared per-turn allowlist. Returns trace counts, unauthorized tool-call evidence, canon mapping VC-AI-TOOL-0001, and claim-boundary guardrails. Backed by T-IB-25/T-IB-29/T-I

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html