zeroleaks - AI Security Scanner - Test your AI systems for pro

项目说明

ZeroLeaks

Red-team your LLM system prompts and agent instructions from the command line.

![npm ]()

What it does

ZeroLeaks loads your system prompt into a model you choose, attacks that model the way a real ad would, then tells you how it held up. E runs on your machine with your own model-provider keys. There are two kinds of tests:

The target is the model plus your prompt. No tools run, and no application code or memory is in.

This package ZeroLeaks

This repo is a standalone, source-a scanner for system prompts, shipped as a CLI and a TypeScript library. Runs are unlimited, and you pay your model provider (OpenRouter, OpenAI, or any OpenAI-compatible endpoint) directly.

zeroleaks.ai is the hosted product, and it tests something else. It red-teams a running AI agent, including its tools, memory, credentials, and the other agents it talks to. It profiles the agent, derives the rules the agent must ne, and attacks those rules on every change. New attack techniques ship there first.

Hosted agent scans don't try to extract the system prompt. They check what sensitive data leaks from the agent's context, such as credentials, internal hosts, and tool schemas, and start with a short reconnaissance of the agent. The hosted API no longer runs prompt scans, so this package is where you test a system prompt on its own.

| | This repo | Hosted (zeroleaks.ai) |
|---|---|---|
| Price | Free to use under the FSL; you pay your model provider | Paid plans (Pro, Team, Business, Enterprise). No free plan; Pro has a 14-day trial |
| Setup | npm install, bring your own model-provider key | Link an agent endpoint, or run scans from your app with /sdk |
| Scans | Unlimited | Unlimited on every plan, with a per-plan cap on concurrent and hourly scans |
| Target | A model running your system prompt | Your deployed or in-process agent, with real tool calls traced |
| Scope | Extraction + injection on a system prompt | Agent boundary, secrets-in-context, multi-agent, artifact, and long-horizon campaigns |
| Corpus | The published probe set | The latest techniques. New attacks land here first |
| Interface | CLI + library | Web dashboard, REST API, and SDK |
| Output | Colorized terminal report + JSON | Stored reports with a policy or config fix per finding, PDF export |
| History | Whatever you save | Stored and trended over time |
| CI/CD | Roll your own (exit 1 on findings, 2 when a scan can't reach a ) | REST API and /sdk |
| Support | GitHub issues | Priority support on Business and Enterprise |

Features

Tech stack

| Component | Technology |
|-----------|------------|
| Runtime | Bun |
| Language | TypeScript |
| LLM provider | OpenRouter (default) or OpenAI direct |
| AI SDK | AI SDK |
| Architecture | Multi-agent orchestration |

Installation

Quick start

CLI usage

Scan options

| Flag | Description |
|------|-------------|
| -m, --mode <mode> | extraction, injection, or dual (default) |
| --injection-category <list> | Filter probes: extraction, tool_hijacking, indirect_injection, authority_exploit, multi_turn, protocol_exploit |
| --se <list> | Filter probes by critical, high, medium, low |
| --max-probes <n> | Cap injection probes (0 = all, default 20; se) |
| --no-multi-turn | Skip multi-turn grooming probes |
| -d, --duration <ms> | Time budget; 0 = no limit, otherwise more than 30000 (the last 30 s is kept for wrap-up) |
| --injection-model <model> | Model for the compliance judge (defaults to the e model) |
| --base-url <url> | Send models to an OpenAI-compatible endpoint (see Pro) |
| -o, --output <file> | Write the full JSON result to a file |
| --json | Print the result as JSON to stdout |
| --no-color / -q, --quiet | Disable color / suppress the progress spinner |

Exit codes

| Code | Meaning |
|------|---------|
| 0 | Every check that ran was graded and nothing was found |
| 1 | were found |
| 2 | No : invalid options, a failed scan, checks that errored and could not be graded, or an -o report that could not be saved |

--turns, --max-probes, and --duration cap how much gets checked, and the summary says when the time budget cut a scan short. A scan ne secure for checks it could not complete. If the target, e, or judge fails and nothing was found in the checks that did run, the is inconclusive and the report lists each failed turn or probe with its error.

API reference

runSecurityScan(systemPrompt, options?)

Most scans only need this. Pass a system prompt and optional settings.

createScanEngine(config?)

Use the engine directly to tune tree depth, branching, and which attack stages run.

Attack categories

| Category | Description |
|----------|-------------|
| direct | Straightforward extraction requests |
| encoding | Base64, ROT13, Unicode bypasses |
| persona | DAN, De Mode, roleplay attacks |
| social | Authority, urgency, reciprocity exploits |
| technical | Format injection, context manipulation |
| crescendo | Multi-turn trust escalation |
| many_shot | Context priming with examples |
| cot_hijack | Chain-of-thought manipulation |
| policy_puppetry | YAML/JSON format exploitation |
| ascii_art | obfuscation techniques |
| injection | Prompt injection attacks |
| hybrid | Combined XSS/CSRF-style attacks |
| tool_exploit | MCP and tool-calling exploits |
| siren | Trust-building manipulation sequences |
| echo_chamber | Gradual escalation through agreement |

Beha injection categories

The injection scan draws from its own beha corpus. Run zeroleaks categories for li.

| Category | Description |
|----------|-------------|
| extraction | System-prompt / instruction extraction |
| tool_hijacking | Make the agent call tools maliciously (curl exfil, SSRF, reverse shell) |
| indirect_injection | Hidden instructions in documents, code, JSON, email, calendars |
| authority_exploit | Fake system/admin/compliance messages |
| multi_turn | Grooming across turns, then escalating |
| protocol_exploit | MCP shadowing, tool-description poisoning, rules-file abuse |

Scan results

Pro

By default every model runs through OpenRouter, so any OpenRouter slug works (anthropic/..., x-ai/..., openai/..., etc.).

If OPENAI_API_KEY is set, OpenAI-style ids such as openai/gpt-5, gpt-5, and o3-mini go straight to the OpenAI API instead. One scan can mix pro, for example an OpenAI target with an OpenRouter attacker:

OpenAI-compatible endpoints

Any server that speaks the OpenAI chat completions API works: Ollama, vLLM, LM Studio, llama.cpp, LiteLLM, Azure, Together, Groq, and so on. Pass its URL with --base-url (or set OPENAI_BASE_URL). With no OpenRouter key, every model goes to that endpoint, whatever its id. Local servers don't need a key.

For a hosted endpoint, add its key with --openai-api-key.

If you also have an OpenRouter key, only OpenAI-style ids go to the endpoint and the rest go to OpenRouter. Prefix a model with openai/ to send it to the endpoint anyway. The prefix is stripped, so openai/llama3.1:8b reaches the server as llama3.1:8b:

En

| | Description |
|----------|-------------|
| OPENROUTER_API_KEY | OpenRouter key; used for all models by default |
| OPENAI_API_KEY | Optional. Routes openai/* and gpt-*/o* models to the OpenAI API |
| OPENAI_BASE_URL | Optional. An OpenAI-compatible endpoint, same as --base-url |

Set at least one key, or a base URL for a local server. Get an OpenRouter key at openrouter.ai.

Research references

The probes and attack patterns borrow from this published work and tooling:

Contributing

Contributions are welcome. Please open an issue first to discuss what you'd like to change.

bun test runs the end-to-end suite in test/e2e/. It drives the real CLI against a local mock LLM, so it needs no API key and makes no network calls. Each run writes its reports and a summary.md to test/e2e/artifacts/.

License

FSL-1.1-Apache-2.0 (Functional Source License)

Copyright (c) 2026 ZeroLeaks

ZeroLeaks is source-a, not open source. You can use, modify, and redistribute it for any purpose except offering a competing commercial product or service. Each release converts to Apache 2.0 on the Change Date in LICENSE, which is two years after the release is published or January 21, 2028, whiche first.

---

For custom quotas, SLAs, or dedicated support, contact us.

项目信息

开发语言：TypeScript

Star 数：732

技术要点

该项目属于安全软件方向的开源资源，代码结构清晰，适合安全研究人员学习参考。项目围绕AI Security Scanner - Test your AI systems for prompt injection and extraction vulnerabilities展开，提供了可运行的实现，对理解相关安全机制、工具原理与攻防技术具有较高的研究价值。

从技术实现角度看，此类项目的核心在于对底层原理的深入理解与工程化落地。开发者在研究过程中可以结合官方文档与社区讨论，梳理项目的初始化流程、核心模块职责与数据流转，逐步掌握其中的技术细节与设计思路。

使用与学习建议

1. 下载源码压缩包，解压到本地环境。

2. 根据项目类型准备对应的运行环境与依赖。

3. 按照 README 中的步骤完成配置与部署。

4. 在隔离的测试环境中运行验证，避免影响生产系统。

免责声明

本资源来源于开源社区，仅供安全研究、技术学习与合法授权范围内的攻防演练使用，请勿用于任何非法或侵害他人权益的用途。使用本项目产生的一切后果由使用者自行承担。