经 AI Skill Hub 精选评估,AI代理Vault代理 获评「推荐使用」。这款Agent工作流在功能完整性、社区活跃度和易用性方面表现出色,AI 评分 7.5 分,适合有一定技术背景的用户使用。
实时生成API密钥,保护AI代理和进程安全
AI代理Vault代理 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。
实时生成API密钥,保护AI代理和进程安全
AI代理Vault代理 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 agent-vault-proxy
# 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 agent-vault-proxy
# 方式三:从源码安装(获取最新功能)
git clone https://github.com/inflightsec/agent-vault-proxy
cd agent-vault-proxy
pip install -e .
# 验证安装
python -c "import agent_vault_proxy; print('安装成功')"
# 命令行使用
agent-vault-proxy --help
# 基本用法
agent-vault-proxy input_file -o output_file
# Python 代码中调用
import agent_vault_proxy
# 示例
result = agent_vault_proxy.process("input")
print(result)
# agent-vault-proxy 配置文件示例(config.yml) app: name: "agent-vault-proxy" debug: false log_level: "INFO" # 运行时指定配置文件 agent-vault-proxy --config config.yml # 或通过环境变量配置 export AGENT_VAULT_PROXY_API_KEY="your-key" export AGENT_VAULT_PROXY_OUTPUT_DIR="./output"
Just-in-time API keys for AI agents - and any other process you route through it: the caller only ever sees a placeholder.
Your agent (dev laptop, CI runner, cron job, etc) gets a fake placeholder string (like sk-PLACEHOLDER-...) and uses it as if it were a real API key. This proxy sits between the caller and the internet, and swaps the fake for the real secret at the last possible moment - on the way out to the upstream API. If the caller gets prompt-injected, dumps a log, or runs a program with a software-supply-chain issue, the only thing that escapes is the fake placeholder. The real key never enters the calling process.
Under the hood: a loopback HTTPS proxy that fetches credentials from Bitwarden Secrets Manager — cloud or self-hosted — just-in-time and injects them into outbound requests, so the calling process never holds the real credential bytes in its address space.
Three steps. Once you've done this, every new API key is just "add to Bitwarden + a few lines of YAML + restart": see Add a secret below.
<details open> <summary><b>Linux (recommended — hardened systemd install)</b></summary>
Full walkthrough: docs/install-systemd.md. ~10 minutes the first time. The doc:
avp UNIX user with no shell, no home directory,pip install --only-binary :all: agent-vault-proxy==0.4.3) into a system-wide venv at /opt/agent-vault-proxy/.venv — --only-binary :all: refuses source distributions, so a compromised transitive dep can't run code at install time,/etc/agent-vault-proxy/bws-token (root-owned, avp-readable) and your bindings at /etc/agent-vault-proxy/bindings.yaml,ProtectSystem=strict, RestrictAddressFamilies, syscall filter, chattr +a append-only audit log) — sandbox controls Docker can't offer.Token, bindings, audit log, and CA cert all live under /etc/agent-vault-proxy/ and /var/{lib,log}/agent-vault-proxy/. </details>
<details> <summary><b>Cross-platform / quick start (macOS, Windows-WSL2, or a Linux dev box)</b></summary>
# Pick a tagged release, not `main` — tags are how you opt into a vetted
# version. Tracking `main` exposes you to a window where a compromised
# maintainer account could push a malicious commit before anyone notices.
git clone -b v0.4.3 --depth 1 https://github.com/inflightsec/agent-vault-proxy && cd agent-vault-proxy
mkdir -p secrets && bash -c '( umask 077 && read -rsp "BWS access token: " T && printf "%s" "$T" > secrets/bws-token && echo )'
cp bindings.example.yaml bindings.yaml && $EDITOR bindings.yaml
docker compose up -d
Faster setup; weaker isolation than systemd. Threat model + caveats in docs/docker.md.
⚠️ Two hard prerequisites for the Docker path: (1) your AI agent's UID must NOT have docker daemon access — docker-group membership ≈ host root, which lets the agentdocker execthe CA private key + BWS token out of the proxy. (2) Do NOT add other containers to the proxy'savp-netnetwork. If either is hard to guarantee on your host, use the systemd install path instead.
A pre-built, cosign-signed container image at ghcr.io/inflightsec/agent-vault-proxy:<tag> is planned for v0.5.0 — cosign verify + docker pull will replace the clone-and-build step. Until then, build locally from the cloned tag. </details>
First, copy the mitmproxy-generated CA cert into the calling shell's working dir. The location depends on install path:
# systemd install (see install-systemd.md step 5):
sudo cp /etc/agent-vault-proxy/ca.pem ./ca.pem && sudo chown "$USER" ./ca.pem
# Docker install:
docker cp agent-vault-proxy:/var/lib/agent-vault-proxy/.mitmproxy/mitmproxy-ca-cert.pem ./ca.pem
Then point the agent at the proxy + give it the placeholder:
export HTTPS_PROXY="http://127.0.0.1:14322" NODE_EXTRA_CA_CERTS="$PWD/ca.pem" SSL_CERT_FILE="$PWD/ca.pem"
export GITHUB_PAT="github_pat_PLACEHOLDER_01HXY1234ABCDEFGHIJ"
curl -H "Authorization: Bearer $GITHUB_PAT" https://api.github.com/user
export GITHUB_PAT="github_pat_PLACEHOLDER_01HXY1234" export HTTPS_PROXY="http://127.0.0.1:14322"
secrets: GITHUB_PAT: placeholder: "github_pat_PLACEHOLDER_01HXY1234" # the agent's env holds THIS inject: header: "Authorization" format: "Bearer {GITHUB_PAT}" # {GITHUB_PAT} = real value AVP fetches # from your backend for the entry above. # {secret} also works as a generic alias. bindings: - host: "api.github.com" # only swapped for this destination methods: [POST] # agent can open things... paths: ["/repos///pulls"] # ...but only "open a PR" - not delete, not merge
bash
高质量的AI工作流API密钥管理工具
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。
✅ MIT 协议 — 最宽松的开源协议之一,可自由商用、修改、分发,仅需保留版权声明。
AI Skill Hub 点评:AI代理Vault代理 的核心功能完整,质量良好。对于自动化工程师和运维人员来说,这是一个值得纳入个人工具库的选择。建议先在非生产环境试用,再逐步推广。
| 原始名称 | agent-vault-proxy |
| 原始描述 | 开源AI工作流:Just-in-time API keys for AI agents - and any other process you route through it。⭐11 · Python |
| Topics | AI代理VaultPython |
| GitHub | https://github.com/inflightsec/agent-vault-proxy |
| License | MIT |
| 语言 | Python |
收录时间:2026-06-03 · 更新时间:2026-06-03 · License:MIT · 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