deepsec - Deepsec is a security harness for finding vulnerab

项目说明

deepsec

deepsec is an agent-powered scanner that you can run in your own infrastructure, optimized to perform on-demand review of all code in existing
large-scale repos.

deepsec is designed to surface hard-to-find issues that have been lurking in applications for a long time. It is configured to use the best models at maximum thinking levels (tunable via --thinking-level, see models), meaning scans can cost thousands or e of dollars for large codebases. Our customers ha the cost worth it for how quickly they were able to patch that would ha gone unfixed.

For large codebases, work fans out across worker machines in parallel.
If a run is interrupted or errors out partway through, just re-run the same
command — deepsec picks up where it left off, skipping files it already
analyzed and only in the rest.

<p>
<a href=" alt=" Labs Product" src=" height="28"></a>
<a href=" alt="npm : deepsec" src=" height="28"></a>
<a href=" alt="License: Apache-2.0" src=" height="28"></a>
<a href=" alt="npm downloads per month: deepsec" src=" height="28"></a>
</p>

Get started

From the root of the repository you want to scan:

The command guides you through e. It asks you to pick an AI model
(with benchmark scores and prices to compare) and how to pay for model
usage — your own OpenAI/Anthropic API key, or AI Gateway — and then
works unattended: it studies your codebase, scans it, and runs the AI
review. The only thing it adds to your repository is a .deepsec/ folder
where all of its state and findings live.

If the run is interrupted for any reason — Ctrl-C, lost connection, a
spending limit — run npx deepsec init again and it continues where it
left off. To cap what a run may spend or how long it may take:

When the scan finishes, get a readable report:

For later scans, work from inside .deepsec/:

The getting started guide
covers all of this in more detail, including using your own OpenAI or
Anthropic API key and running from CI or a coding agent.

Docs

After initialization, agents can read the exact documentation matching the
installed CLI at .deepsec/node_modules/deepsec/SKILL.md and
.deepsec/node_modules/deepsec/dist/docs/. Setup errors expose these as
absolute machine-readable paths.

AI provider

By default, deepsec routes model calls through AI Gateway, which
gi to every major model without pro keys. You can
instead bring your own key — OpenAI, Anthropic, or a custom HTTPS
provider — by passing --model-auth direct with --ai-provider and
--ai-api-key-env to init; no account is needed in that mode.
Deepsec only e the *name* of the en holding
your key, never the key itself. See
project link and credentials
for the full reference.

If a process or re run halts because the upstream credential
ran out of quota or credits, deepsec stops gracefully and tells you
where to top up. Re-run the same command afterward and it picks up
where it left off.

Distributed execution (optional)

Large monorepos can fan work across Sandbox microVMs:

Setup already the connection, so this needs no extra
onboarding. The local working tree is tarballed and uploaded; .git is
excluded. Model credentials remain host-side and are injected only at the
selected egress host.

Security model of deepsec itself

Treat deepsec like a coding agent with full shell access on the en that it is
running on. It is designed to run on trusted inputs (your source code) but you may still
be concerned about prompt injection due to external dependencies or code.

Running on a sandbox (see above) does limit the potential exposure substantially:

Workflow reference

| Command | What it does |
|-----------------|----------------------------------------------------------|
| scan | Find candidate sites with regex matchers (fast, no AI) |
| process | AI in; emits findings + recommendation |
| process --diff| PR-mode: scan + in only files changed in a diff |
| triage | Lightweight P0/P1/P2 classification (cheaper model) |
| re | Re-check existing findings; checks git history for fixes |
| enrich | Add git committer info + (with a plugin) ownership data |
| report | Markdown + JSON summary for one project |
| export | Per-finding JSON or directory of markdown files |
| metrics | Cross-project counts: se, vulns by type, TPs |
| status | Snapshot of the project mirror |
| sandbox <cmd> | Run any of the above on Sandbox microVMs |

License

Apache 2.0. See LICENSE and NOTICE.

项目信息

开发语言：TypeScript

Star 数：8100

技术要点

该项目属于漏洞知识库方向的开源资源，代码结构清晰，适合安全研究人员学习参考。项目围绕Deepsec is a security harness for finding vulnerabilities in your codebase powered by coding agents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。