Agent skill

API Relay Audit

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.

★ 709 stars AGPL-3.0 toby-bridges/api-relay-audit

Install this skill

This command installs the skill into the portable ~/.agents/skills directory. The homepage installer can generate the native path for your specific agent.

mkdir -p $HOME/.agents/skills/'api-relay-audit' && curl -fsSL 'https://raw.githubusercontent.com/toby-bridges/api-relay-audit/HEAD/skills/api-relay-audit/SKILL.md' -o $HOME/.agents/skills/'api-relay-audit'/SKILL.md

View raw SKILL.md View repository

Skill details

Repository: toby-bridges/api-relay-audit
SKILL.md path: skills/api-relay-audit/SKILL.md
Author: toby-bridges
Tags: agents, ai-agents, ai-audit, ai-security, anthropic, api-gateway, claude, cli, llm-audit, llm-proxy