Connection check
verified live · 26h ago
injection-detector
Formally-verified injection/exfiltration detector for AI agents (MCP-02).
Tools
2
GitHub stars
—
Installs / wk
—
Licence
—
Transport
streamable-http
Last checked
26h ago
Tools & capabilities
2 toolsRead from the running server on 26h ago.
detect_injection
input*agentIdcontextcertainty
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… 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.
detect_trace_tool_policy
tracetracestargetName