Local security audit for AI API relays and LLM proxies: detects prompt injection, model substitution, tool-call rewriting, SSE anomalies, error leakage, and Web3 wallet risks.
-
Updated
Jul 25, 2026 - Python
Local security audit for AI API relays and LLM proxies: detects prompt injection, model substitution, tool-call rewriting, SSE anomalies, error leakage, and Web3 wallet risks.
Verify which LLM an OpenAI-compatible API really serves — single-token behavioral fingerprinting (Jensen-Shannon) from the paper "One Token Is Enough" (arXiv:2607.10252). Zero-dependency TypeScript library + CLI. Catches model substitution by resellers & gateways.
Which model is really behind your API relay or agent IDE? Behavioral fingerprinting + anytime-valid sequential tests (FPR<=1%). LLMs can't be random - measured on 9 frontier models.
一个用 TEE 远程证明和响应签名实现的用户可验证 AI 中转方案。 A user-verifiable AI relay design implemented with TEE remote attestation and response signing.
CLI framework for auditing LLM providers and detecting model substitution.
Add a description, image, and links to the model-substitution topic page so that developers can more easily learn about it.
To associate your repository with the model-substitution topic, visit your repo's landing page and select "manage topics."