Skip to content
Back to search

agentic-radar

A security scanner for your LLM agentic workflows

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 11 Nov 2026.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/splx-ai/agentic-radar with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/splx-ai/agentic-radar'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/splx-ai--agentic-radar/badge.svg)](/listings/splx-ai--agentic-radar)

HTML

<a href="/listings/splx-ai--agentic-radar"><img src="/api/listings/splx-ai--agentic-radar/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Prerequisites

There are none! Just make sure you have Python (pip) installed on your machine.

Installation

pip install agentic-radar

# Check that it is installed
agentic-radar --version

Some features require extra installations, depending on the targeted agentic framework. See more [below](#advanced-installation).

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 351 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. <div align="center">
  2. <a href="https://splx.ai">
  3. <img src="https://github.com/splx-ai/agentic-radar/raw/main/docs/logo.png" alt="logo" width="600" height="auto" />
  4. </a>
  5. <p>
  6. A Security Scanner for your agentic workflows!
  7. </p>
  8. <!-- Badges -->
  9. <p>
  10. <a href="https://github.com/splx-ai/agentic-radar/graphs/contributors">
  11. <img src="https://img.shields.io/github/contributors/splx-ai/agentic-radar" alt="contributors" />
  12. </a>
  13. <a href="">
  14. <img src="https://img.shields.io/github/last-commit/splx-ai/agentic-radar" alt="last update" />
  15. </a>
  16. <a href="https://github.com/splx-ai/agentic-radar/network/members">
  17. <img src="https://img.shields.io/github/forks/splx-ai/agentic-radar" alt="forks" />
  18. </a>
  19. <a href="https://github.com/splx-ai/agentic-radar/stargazers">
  20. <img src="https://img.shields.io/github/stars/splx-ai/agentic-radar" alt="stars" />
  21. </a>
  22. <a href="https://github.com/splx-ai/agentic-radar/issues/">
  23. <img src="https://img.shields.io/github/issues/splx-ai/agentic-radar" alt="open issues" />
  24. </a>
  25. <a href="https://github.com/splx-ai/agentic-radar/blob/main/LICENSE">
  26. <img src="https://img.shields.io/github/license/splx-ai/agentic-radar.svg" alt="license" />
  27. </a>
  28. <a href="https://pypi.org/project/agentic-radar">
  29. <img src="https://img.shields.io/pypi/v/agentic-radar" alt="PyPI - Version" />
  30. </a>
  31. <a href="https://pypi.org/project/agentic-radar">
  32. <img src="https://static.pepy.tech/badge/agentic-radar" alt="PyPI - Downloads" />
  33. </a>
  34. <br />
  35. <a href="https://discord.gg/tR2d54utZc">
  36. <img src="https://img.shields.io/discord/1346578514177949767?style=for-the-badge&logo=discord&logoColor=white&label=Discord&labelColor=5865F2&color=555555" alt="Discord" />
  37. </a>
  38. <a href="https://join.slack.com/t/splxaicommunity/shared_invite/zt-31b3hc3mt-A0v78qztTIMSNBg6y~WOAA">
  39. <img src="https://img.shields.io/badge/Slack-4A154B?style=for-the-badge&logo=slack&logoColor=white" alt="Slack" />
  40. </a>
  41. </p>
  42. <h4>
  43. <a href="https://github.com/splx-ai/agentic-radar/">View Demo</a>
  44. <span> · </span>
  45. <a href="https://github.com/splx-ai/agentic-radar">Documentation</a>
  46. <span> · </span>
  47. <a href="https://github.com/splx-ai/agentic-radar/issues/">Report Bug</a>
  48. <span> · </span>
  49. <a href="https://github.com/splx-ai/agentic-radar/issues/">Request Feature</a>
  50. </h4>
  51. </div>
  52. <img src="docs/overview_image.png"/>
  53. <!-- TABLE OF CONTENTS -->
  54. <details>
  55. <summary>Table of Contents</summary>
  56. <ol>
  57. <li>
  58. <a href="#description-">Description</a>
  59. </li>
  60. <li>
  61. <a href="#agentic-visualizer-">Agentic Visualizer</a>
  62. </li>
  63. <li>
  64. <a href="#getting-started-">Getting Started</a>
  65. <ul>
  66. <li><a href="#prerequisites">Prerequisites</a></li>
  67. <li><a href="#installation">Installation</a></li>
  68. </ul>
  69. </li>
  70. <li>
  71. <a href="#advanced-installation">Advanced Installation</a>
  72. <ul>
  73. <li><a href="#crewai-installation">CrewAI Installation</a></li>
  74. <li><a href="#openai-agents-installation">OpenAI Agents Installation</a></li>
  75. </ul>
  76. </li>
  77. <li><a href="#usage">Usage</a></li>
  78. <li>
  79. <a href="#advanced-features-">Advanced Features</a>
  80. <ul>
  81. <li><a href="#agentic-prompt-hardening">Agentic Prompt Hardening</a></li>
  82. <li><a href="#-test-for-vulnerabilities-in-agentic-workflows">Test for Vulnerabilities in Agentic Workflows</a></li>
  83. <li><a href="#cicd-workflow">CI/CD Workflow</a></li>
  84. </ul>
  85. </li>
  86. <li><a href="#roadmap-">Roadmap</a></li>
  87. <li><a href="#blogs-and-tutorials-">Blogs and Tutorials</a></li>
  88. <li><a href="#community-">Community</a></li>
  89. <li><a href="#frequently-asked-questions-">Frequently Asked Questions</a></li>
  90. <li><a href="#contributing-">Contributing</a></li>
  91. <li><a href="#code-of-conduct-">Code Of Conduct</a></li>
  92. <li><a href="#license-">License</a></li>
  93. </ol>
  94. </details>
  95. ## Description 📝
  96. The **Agentic Radar** is designed to analyze and assess agentic systems for security and operational insights. It helps developers, researchers, and security professionals understand how agentic systems function and identify potential vulnerabilities.
  97. It allows users to create a security report for agentic systems, including:
  98. 1. **Workflow Visualization** - a graph of the agentic system's workflow✅
  99. 2. **Tool Identification** - a list of all external and custom tools utilized by the system✅
  100. 3. **MCP Server Detection** - a list of all MCP servers used by system's agents✅
  101. 4. **Vulnerability Mapping** - a table connecting identified tools to known vulnerabilities, providing a security overview✅
  102. The comprehensive HTML report summarizes all findings and allows for easy reviewing and sharing.
  103. **[View Full Report Example Here](https://agentic-radar.neocities.org/)**
  104. **Agentic Radar** includes mapping of detected vulnerabilities to well-known security frameworks 🛡️.
  105. + [OWASP Top 10 LLM Applications](https://owasp.org/www-project-top-10-for-large-language-model-applications/)
  106. + [OWASP Agentic AI – Threats and Mitigations](https://genaisecurityproject.com/resource/agentic-ai-threats-and-mitigations)
  107. ## Agentic Visualizer 🎆
  108. If you only care about visualization, try out the [Agentic Visualizer](https://agentic-visualizer.splx.ai/).
  109. It is a web-based tool that allows you to visualize agentic workflows in a user-friendly way.
  110. ## Getting Started 🚀
  111. ### Prerequisites
  112. There are none! Just make sure you have Python (pip) installed on your machine.
  113. ### Installation
  114. ```sh
  115. pip install agentic-radar
  116. # Check that it is installed
  117. agentic-radar --version
  118. ```
  119. Some features require extra installations, depending on the targeted agentic framework. See more [below](#advanced-installation).
  120. ## Advanced Installation
  121. ### CrewAI Installation
  122. CrewAI extras are needed when using one of the following features in combination with CrewAI:
  123. - [Agentic Radar Test](#-test-for-vulnerabilities-in-agentic-workflows)
  124. - Descriptions for predefined tools
  125. You can install Agentic Radar with extra CrewAI dependencies by running:
  126. ```sh
  127. pip install "agentic-radar[crewai]"
  128. ```
  129. > [!WARNING]
  130. > This will install the `crewai-tools` package which is only supported on Python versions >= 3.10 and < 3.13.
  131. > If you are using a different python version, the tool descriptions will be less detailed or entirely missing.
  132. ### OpenAI Agents Installation
  133. OpenAI Agents extras are needed when using one of the following features in combination with OpenAI Agents:
  134. - [Agentic Radar Test](#-test-for-vulnerabilities-in-agentic-workflows)
  135. You can install Agentic Radar with extra OpenAI Agents dependencies by running:
  136. ```sh
  137. pip install "agentic-radar[openai-agents]"
  138. ```
  139. ## Usage
  140. Agentic Radar now supports two main commands:
  141. ### 1. `scan`
  142. Scan code for agentic workflows and generate a report.
  143. ```sh
  144. agentic-radar scan [OPTIONS] FRAMEWORK:{langgraph|crewai|n8n|openai-agents|autogen}
  145. ```
  146. Example:
  147. ```sh
  148. agentic-radar scan langgraph -i path/to/langgraph/example/folder -o report.html
  149. ```
  150. ---
  151. ### 2. `test`
  152. Test agents in an agentic workflow for various vulnerabilities.
  153. Requires OPENAI_API_KEY set as environment variable.
  154. ```sh
  155. agentic-radar test [OPTIONS] FRAMEWORK:{openai-agents} ENTRYPOINT_SCRIPT_WITH_ARGS
  156. ```
  157. Example:
  158. ```sh
  159. agentic-radar test openai-agents "path/to/openai-agents/example.py"
  160. ```
  161. See more about this feature [here](#-test-for-vulnerabilities-in-agentic-workflows).
  162. ## Advanced Features ✨
  163. ### Agentic Prompt Hardening
  164. Agentic Prompt Hardening automatically improves detected system prompts in your agentic workflow and displays them in the report. It transforms simple agent instructions into high-quality structured system prompts which follow best prompt engineering practices.
  165. > [!NOTE]
  166. > Currently supported frameworks (with more to come): OpenAI Agents, CrewAI, Autogen
  167. It is quite straightforward to use:
  168. 1. Set your OPENAI_API_KEY environment variable by running `export OPENAI_API_KEY=<api_key>`. Alternatively, pass a .env file explicitly with `--env-file path/to/.env` (Agentic Radar never loads a .env file automatically).
  169. 2. Run Agentic Radar with the `--harden-prompts` flag, for example:
  170. ```sh
  171. agentic-radar scan openai-agents --harden-prompts -i examples/openai-agents/
  172. basic/lifecycle_example -o report.html
  173. ```
  174. 4. Inspect hardened system prompts in the generated report:
  175. <img src="docs/prompt_hardening.png"/>
  176. ### 🔍 Test for Vulnerabilities in Agentic Workflows
  177. Agentic Radar now supports testing your agent workflows at **runtime** to identify critical vulnerabilities through simulated adversarial inputs.
  178. This includes automated testing for:
  179. - Prompt Injection
  180. - PII Leakage
  181. - Harmful Content Generation
  182. - Fake News Generation
  183. Currently supported for:
  184. - OpenAI Agents ✅ (more frameworks coming soon)
  185. #### 🛠 How It Works
  186. The test command launches your agentic workflow with a test suite designed to simulate malicious or adversarial inputs. These tests are designed based on real-world attack scenarios aligned with the OWASP LLM Top 10.
  187. > [!NOTE]
  188. > This feature requires OPENAI_API_KEY or AZURE_OPENAI_API_KEY set as an environment variable. You can set it via command line or load it from a .env file with `--env-file path/to/.env`.
  189. Test is run like:
  190. ```sh
  191. agentic-radar test <framework> "<path/to/the/workflow/main.py any-necessary-args>"
  192. ```
  193. For example:
  194. ```sh
  195. agentic-radar test openai-agents "examples/openai-agents/basic/lifecycle_example.py"
  196. ```
  197. The tool injects itself into the agentic workflow provided by user, detects necessary information and runs the prepared tests.
  198. #### Configurable Tests
  199. You can pass custom tests to Agentic Radar by creating a YAML file with the following structure:
  200. ```yaml
  201. include_default_tests: false
  202. tests:
  203. - name: TestA
  204. input: Mention A.
  205. success_condition: Attack succeeded if A is mentioned.
  206. - name: TestB
  207. input: Mention B.
  208. success_condition: Attack succeeded if B is mentioned.
  209. ```
  210. `name` is the name of the test, `input` is the input text to be passed to the agent, and `success_condition` is a description of what constitutes a successful attack (it will be used by an oracle LLM to determine if the test passed or failed).
  211. You can then run Agentic Radar test with the `--config` option pointing to your YAML file:
  212. ```sh
  213. agentic-radar test openai-agents --config custom_tests.yaml "examples/openai-agents/basic/lifecycle_example.py"
  214. ```
  215. By default, Agentic Radar will also include the built-in tests. You can disable them by setting `include_default_tests` to `false` in your YAML file.
  216. #### 📊 Rich Test Results
  217. All test results are printed in a visually rich table format directly in the terminal.
  218. Each row shows:
  219. - Agent name
  220. - Type of test
  221. - Injected input
  222. - Agent output
  223. - ✅ Whether the test passed or failed
  224. - 🛑 A short explanation of the result
  225. This makes it easy to spot vulnerabilities at a glance—especially in multi-agent systems.
  226. <img src="docs/test_results.png" alt="Test Results Example" />
  227. ### CI/CD Workflow
  228. To integrate Agentic Radar into your CI/CD pipeline, you can use the [provided GitHub Actions workflow example](https://github.com/splx-ai/agentic-radar/blob/main/examples/github_workflow/auto-agentic-radar.yaml). Just paste the YAML to the `.github/workflows` directory of your repository.
  229. This workflow automatically runs Agentic Radar scans on your codebase whenever changes are pushed to the repository. The generated report is uploaded as an artifact in the GitHub Actions run.
  230. ## Roadmap 📈
  231. This matrix shows which agentic frameworks support all the Agentic Radar features. With time we will strive towards covering all current frameworks with all existing features, as well as introducing new frameworks to the mix.
  232. | Feature | Scan | MCP Detection | Prompt Hardening | Agentic Test
  233. |----------------|-------------|-------------|-------------|-------------|
  234. | OpenAI Agents | ✅ | ✅ | ✅ | ✅ |
  235. | CrewAI | ✅ | ✅ | ✅ | ❌ |
  236. | n8n | ✅ | ✅ | ❌ | ❌ |
  237. | LangGraph | ✅ | ✅ | ❌ | ❌ |
  238. | Autogen | ✅ | ✅ | ✅ | ❌ |
  239. Are there some features you would like to see happen first? Vote anonymously [here](https://strawpoll.com/w4nWWMqqlnA) or [open a GitHub Issue](https://github.com/splx-ai/agentic-radar/issues/new/choose).
  240. ## Blogs and Tutorials 💡
  241. - [CrewAI](https://splx.ai/blog/enhancing-ai-transparency-scanning-crewai-workflows-with-agentic-radar)
  242. - [n8n](https://splx.ai/blog/scanning-n8n-workflows-with-agentic-radar)
  243. - [OpenAI Agents](https://splx.ai/blog/openai-agents-sdk-transparent-workflows-with-agentic-radar)
  244. - [Autogen](https://colab.research.google.com/drive/14IeJv08lzBsLlEO9cKoHloDioWMWGf5Q)
  245. - [MCP Server Detection](https://splx.ai/blog/agentic-radar-now-detects-mcp-servers-in-agentic-workflows)
  246. - [Agentic Prompt Hardening](https://splx.ai/blog/agentic-radar-now-scans-and-hardens-system-prompts-in-agentic-workflows)
  247. ## Community 🤝
  248. We welcome contributions from the AI and security community! Join our [Discord community](https://discord.gg/QZQpef5PsD) or [Slack community](https://join.slack.com/t/splxaicommunity/shared_invite/zt-31b3hc3mt-A0v78qztTIMSNBg6y~WOAA) to connect with other developers, discuss features, get support and contribute to **Agentic Radar** 🚀
  249. If you like what you see, give us a star! It keeps us inspired to improve and innovate and helps others discover the project 🌟
  250. ## Frequently Asked Questions ❓
  251. **Q: Is my source code being shared or is everything running locally?**
  252. A: The main features (static workflow analysis and vulnerability mapping) are run completely locally and therefore your code is not shared anywhere. For optional advanced features, LLM's might be used. Eg. when using [Prompt Hardening](#agentic-prompt-hardening), detected system prompts can get sent to LLM for analysis.
  253. ## Contributing 💻
  254. [CONTRIBUTING](CONTRIBUTING.md)
  255. ## Code Of Conduct 📜
  256. [CODE OF CONDUCT](CODE_OF_CONDUCT.md)
  257. ## License ⚖️
  258. [LICENSE](LICENSE)

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.