Enterprise DNAEnterprise DNA
OOpen SourceObservabilitymedium

API Relay Audit

by Community

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.

Visit siteView repoSubmit your build →

OSS

API Relay Audit

Added 1 Oct 2026

#ai-agents#ai-audit#ai-security#anthropic#api-gateway#claude#dsh-plugin#llm-audit
Catalogue record, not a reviewed recommendation. This record can include automatically collected descriptions and setup details. Confirm important claims with the original source. Explore source-reviewed tools.

Overview

Local security audit tool for AI API relays and LLM proxies. Written in Python, it inspects relay traffic to detect prompt injection, model substitution, tool-call rewriting, SSE anomalies, error leakage, and Web3 wallet risks.

Best for

Best for
Developers securing self-hosted AI API relays and LLM proxies.

Use cases

  • Audit an AI API relay for prompt injection vectors
  • Verify LLM proxy responses for model substitution
  • Inspect SSE streams and error responses for leakage

Notes

866 stars on GitHub. Last updated 2026-09-16. Licensed AGPL-3.0.

Pros

  • Runs locally, keeping traffic in-house
  • Covers multiple attack surfaces in one tool
  • Open source with 866 stars and Python ecosystem

Cons

  • Audit is point-in-time, not continuous monitoring
  • Requires manual setup and traffic capture
  • Community project, support may be limited
Free 27-page guide

Get the free Developer’s Field Guide

A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.

Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.

No spam. Unsubscribe any time.

← Back to Open SourceSubmit your own entry →