PrismorSec/prismor

232 stars · Last commit 2026-07-12

Runtime Firewall for AI agents which catches the rogue tool call before it runs. Dangerous commands, secret leaks, prompt injection. For Claude Code, Codex and framework SDKs

README preview

<h1 align="center">Prismor</h1>

<p align="center"><sub>formerly <strong>Immunity Agent</strong></sub></p>

<h3 align="center">Runtime security hooks for Claude Code, Cursor, and other AI coding agents.<br>Blocks dangerous commands, prevents secret leaks, and stops prompt injection in real time.</h3>

<p align="center">
  <a href="https://pypi.org/project/prismor/"><img src="https://img.shields.io/pypi/v/prismor" alt="PyPI"/></a>
  <a href="https://github.com/PrismorSec/prismor/blob/main/LICENSE"><img src="https://img.shields.io/badge/License-Apache_2.0-blue.svg" alt="License" /></a>
  <a href="https://github.com/PrismorSec/prismor"><img src="https://img.shields.io/badge/PRs-welcome-brightgreen.svg" alt="PRs Welcome" /></a>
  <a href="https://x.com/prismor_dev"><img src="https://img.shields.io/badge/@prismor__dev-black?logo=x&logoColor=white" alt="X" /></a>
  <a href="https://deepwiki.com/PrismorSec/prismor"><img src="https://img.shields.io/badge/DeepWiki-prismor-blue?logo=bookstack&logoColor=white" alt="DeepWiki" /></a>
  <a href="https://discord.gg/FH2PRX754c"><img src="https://img.shields.io/badge/Discord-join-5865F2?logo=discord&logoColor=white" alt="Discord" /></a>
</p>

<h3 align="center">
  <a href="https://prismor.dev"><b>Website</b></a> &bull;
  <a href="SKILL.md"><b>Onboard with Skill</b></a> &bull;
  <a href="docs/cli-reference.md"><b>CLI Reference</b></a> &bull;
  <a href="docs/supply-chain.md"><b>Supply Chain</b></a> &bull;

View full repository on GitHub →