AI接口安全审计 是 AI Skill Hub 本期精选Agent工作流之一。综合评分 7.5 分,整体质量较高。我们推荐使用将其纳入你的 AI 工具库,帮助提升工作效率。
AI接口安全审计 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排,将复杂的多步骤任务拆解为清晰的自动化流程,实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成,适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
AI接口安全审计 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排,将复杂的多步骤任务拆解为清晰的自动化流程,实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成,适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
# 方式一:pip 安装(推荐)
pip install api-relay-audit
# 方式二:虚拟环境安装(推荐生产环境)
python -m venv .venv
source .venv/bin/activate # Windows: .venv\Scripts\activate
pip install api-relay-audit
# 方式三:从源码安装(获取最新功能)
git clone https://github.com/toby-bridges/api-relay-audit
cd api-relay-audit
pip install -e .
# 验证安装
python -c "import api_relay_audit; print('安装成功')"
# 命令行使用
api-relay-audit --help
# 基本用法
api-relay-audit input_file -o output_file
# Python 代码中调用
import api_relay_audit
# 示例
result = api_relay_audit.process("input")
print(result)
# api-relay-audit 配置文件示例(config.yml) app: name: "api-relay-audit" debug: false log_level: "INFO" # 运行时指定配置文件 api-relay-audit --config config.yml # 或通过环境变量配置 export API_RELAY_AUDIT_API_KEY="your-key" export API_RELAY_AUDIT_OUTPUT_DIR="./output"
<p align="center"> <img alt="API Relay Audit - AI API Relay Security Audit. Prompt Injection, Model Substitution, Tool Rewriting, SSE Anomalies. Runs locally; your API key is sent only to the relay URL you choose." src="./assets/readme-banner.png"> </p>
API Relay Audit 也可以作为 agent skill 使用。
这些 skill 不给中转站颁发安全认证,只帮助 agent 在信任 relay 前生成本地、可复查的 Markdown 报告。
```bash curl -sO https://raw.githubusercontent.com/toby-bridges/api-relay-audit/master/audit.py
python audit.py --key <YOUR_KEY> --url <BASE_URL> --output report.md
```bash curl -sO https://raw.githubusercontent.com/toby-bridges/api-relay-audit/master/audit.py
python audit.py --key <YOUR_KEY> --url <BASE_URL> --output report.md
- GitHub Pages: toby-bridges.github.io/api-relay-audit - Chinese landing page: toby-bridges.github.io/api-relay-audit/zh/ - Example report: sanitized fixture report - Guides: AI API relay / LLM proxy, Claude relay audit, tool comparison, prompt injection in proxies, Web3 wallet prompt injection, OpenClaw and Hermes skill - Contributors / Credits: CONTRIBUTORS.md - Security policy: SECURITY.md - Contributing guide: CONTRIBUTING.md - Social: X @li9292
<p align="center"> Local security audit for AI API relays and LLM proxies. </p>
<p align="center"> <a href="https://toby-bridges.github.io/api-relay-audit/"><img alt="GitHub Pages" src="https://img.shields.io/badge/GitHub%20Pages-Live%20Site-0a7f5a?style=for-the-badge"></a> <a href="#chinese-readme"><img alt="README 中文" src="https://img.shields.io/badge/README-%E4%B8%AD%E6%96%87-111111?style=for-the-badge"></a> <a href="https://x.com/li9292"><img alt="X @li9292" src="https://img.shields.io/badge/X-%40li9292-111111?style=for-the-badge"></a> <a href="https://github.com/toby-bridges"><img alt="GitHub toby-bridges" src="https://img.shields.io/badge/GitHub-toby--bridges-24292f?style=for-the-badge"></a> </p>
<p align="center"> <a href="./SKILL.md"><strong>OpenClaw Skill</strong></a> · <a href="./skills/api-relay-audit/SKILL.md"><strong>Hermes Skill</strong></a> </p>
API Relay Audit is a local security audit tool for AI API relays and LLM proxies. It detects prompt injection, model substitution, tool rewriting, SSE anomalies, error leakage, and Web3 wallet risks. Your API key is sent only to the relay URL you choose.
Use it when you rely on a third-party AI API relay, OpenAI-compatible proxy, Claude-compatible proxy, or Web3 agent workflow and want a repeatable Markdown report before trusting that relay with production or wallet-related traffic.
audit.py uses only Python stdlib plus curl; your API key is sent only to the relay URL you choose.LOW / MEDIUM / HIGH verdict.An API relay or LLM proxy is a third-party service between you and an AI provider such as Anthropic or OpenAI. It forwards your requests upstream, but it can also inject hidden instructions, swap models, truncate context, rewrite tool output, or leak credentials in error responses.
API Relay Audit runs locally, so your API key is sent only to the relay URL you specify. The standalone version is a single Python file with zero Python package dependencies, which makes it easier to inspect before running.
api-relay-audit 是一个本地运行的 AI API 中转站 / LLM proxy 安全审计工具。它检测 prompt injection、模型替换、工具调用改写、SSE 流异常、错误响应泄漏,以及 Web3 钱包相关风险;你的 API Key 只会发送到你指定的中转站 URL。
当你使用第三方 AI API 中转站、OpenAI-compatible proxy、Claude-compatible proxy,或者 Web3 agent 工作流时,可以用它在信任该中转站之前生成一份可复查的 Markdown 审计报告。
They serve different needs. hvoy.ai is useful for relay reputation lookup, cctest.ai focuses on one-click testing and channel fingerprinting, and API Relay Audit focuses on local, open-source, repeatable security auditing with structured Markdown reports.
高质量的AI安全审计工具
该工具使用 AGPL-3.0 协议,商用场景请仔细阅读协议条款,必要时咨询法律意见。
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
⚠️ AGPL 3.0 — 最严格的 Copyleft,网络服务端使用也需开源,SaaS 使用受限。
经综合评估,AI接口安全审计 在Agent工作流赛道中表现稳健,质量良好。如果你已有明确的使用需求,可以直接上手体验;如果还在评估阶段,建议对比同类工具后再做决策。
| 原始名称 | api-relay-audit |
| 原始描述 | 开源AI工作流:Local security audit for AI API relays and LLM proxies: detects prompt injection。⭐629 · Python |
| Topics | ai安全api网关python |
| GitHub | https://github.com/toby-bridges/api-relay-audit |
| License | AGPL-3.0 |
| 语言 | Python |
收录时间:2026-06-03 · 更新时间:2026-06-03 · License:AGPL-3.0 · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端