rea
Reverse engineer anything with agents, from app behavior down to native binaries.
420k
@morlutoSecurity
Plugin
sage
Checks the shell commands, URL fetches and file writes an AI coding assistant is about to run, and blocks dangerous ones such as reverse shells, command injection and risky credential or supply chain actions before they execute.
Plugin Signal73/100Solid
maintained100
capable34
documented100
adopted53
Claude Code
> /plugin marketplace add gendigitalinc/sage> /plugin install sage@sage
Codex
$ npx skills add gendigitalinc/sage -a codex
Cursor
$ npx skills add gendigitalinc/sage -a cursor
Gemini CLI
$ npx skills add gendigitalinc/sage -a gemini-cli
GitHub Copilot
$ copilot plugin marketplace add gendigitalinc/sage$ copilot plugin install sage@sage
OpenCode
$ npx skills add gendigitalinc/sage -a opencode
Windsurf
$ npx skills add gendigitalinc/sage -a windsurf
Stats
326
Stars
34
Forks
Active
Maintenance
TypeScript
Language
Apache-2.0
License
Last commit
Created
What's inside
README
Sage
Safety for Agents — Agent Detection & Response for AI coding assistants
Sage is a lightweight security layer that protects AI agents from executing dangerous actions. It intercepts tool calls — shell commands, URL fetches, file writes — and checks them against multiple threat detection layers before they run.
Note: Sage may appear under a different product name (e.g., Norton Sage, Avast Sage) depending on how it was installed. See Branding for details.
Key Features
- URL reputation — cloud-based detection of malware, phishing, and scam URLs
- Local heuristics — 300+ YAML-based threat patterns for dangerous commands, suspicious URLs, credential exposure, and obfuscation
- Prompt injection detection — two-tier defense (heuristics + fine-tuned ML model) against injected instructions in fetched content. See Prompt Injection
- Package supply-chain checks — registry existence, file reputation, and age analysis for npm/PyPI packages
- Plugin scanning — scans installed plugins for threats at session start
- AMSI integration — Windows Antimalware Scan Interface support (Windows + WSL via PowerShell interop; no-op on macOS and non-WSL Linux)
Quick Start
Visit ai.gendigital.com/sage for the latest installation instructions, or use the platform-specific guides below.
Claude Code — install guide · requires Node.js >= 18
/plugin marketplace add https://github.com/gendigitalinc/sage.git
/plugin install sage@sage
Cursor — install guide · install the Gen Sage extension from the marketplace
VS Code — install guide · install the Gen Sage extension from the marketplace
OpenClaw — install guide · install from npm
openclaw plugins install @gendigital/sage-openclaw
OpenCode — install from npm by adding to ~/.config/opencode/opencode.json:
{
"plugin": ["@gendigital/sage-opencode"]
}
See the User Guide for detailed instructions, configuration, and troubleshooting.
Privacy
For privacy considerations, please refer to Privacy.
Documentation
| Document | Description |
|---|---|
| User Guide | Installation, usage, configuration, exceptions, platform guides, privacy, FAQ |
| Developer Guide | Architecture, development setup, testing, threat rule format |
| Prompt Injection | ML + heuristic prompt injection detection |
| Package Protection | npm/PyPI supply-chain checks |
| AMSI Scanning | Windows antimalware scanning via AMSI |
| Plugin Scanning | Session-start plugin scanning |
| Audit Log | On-disk JSONL schema (entries, signals, content) |
| MCP Server | Shared MCP server architecture |
| Decision Pipeline | Signal sources, policy model, evaluation order |
| Branding | Product name configuration |
Connectors
| Host | Package | How it hooks |
|---|---|---|
| Claude Code | @gendigital/sage-claude-code | MCP hook tools |
| OpenClaw | @gendigital/sage-openclaw | In-process before_tool_call |
| OpenCode | @gendigital/sage-opencode | In-process plugin |
| Cursor / VS Code / Copilot CLI | sage-cursor | Installed hook script |
| pi | @gendigital/sage-pi | In-process tool_call extension |
| Oh My Pi | @gendigital/sage-omp | In-process hook (--hook) |
Contributing
See CONTRIBUTING.md for development setup, coding conventions, and the threat rule contribution process.
License
Copyright 2026 Gen Digital Inc.
- Source code: Apache License 2.0
- Threat detection rules (
threats/): Detection Rule License 1.1
Stars on GitHub
Momentum
- stars in total
- 326
File tree
Similar plugins.
@morlutoreverse-skill
A skill pack for authorized reverse engineering, security research, and penetration testing that routes tasks to the right skill and sets up needed tools on demand. It covers API security assessment and Android APK analysis, among others.
46 skills44k
@zhaoxuya520cybersecurity-skills
Gives an AI agent the step-by-step workflow a senior security analyst follows, covering when to use each technique, what to check first, how to run it and how to verify the result. Covers incident response, forensics, threat intelligence, malware analysis, penetration testing and red teaming.
200 skills36k
@mukul975watermarks-remover
Agent skill + stdlib Python service to strip multi-vendor AI provenance marks from text and files, for privacy and hygiene on content you own. The skill is a thin client: it drives the machinery over HTTP, so the agent host needs no Python.
2 skills1 hook26k
@guillaumemeyerQuestions about sage.
Install it with the command on its page. It includes security-awareness. Its skills do not fire on their own yet. Free and open source.
- What is sage?
- gendigitalinc/sage is a security plugin that protects AI coding agents from executing dangerous actions, shipping skills and hooks. It adds a security-awareness skill covering safe command execution, URL handling and credential management, so use it when you want guardrails on agent tool use.
- How do I install sage?
- Run these in Claude Code: /plugin marketplace add gendigitalinc/sage then /plugin install sage@sage. Then prompt normally.
- Does sage auto-invoke its skills?
- Not yet. It is indexed on Flowy as a plain plugin.
- Is sage free?
- Yes. Flowy is free and open source, with nothing gated. You can read every skill in full before you install.
- Which coding agents can use sage's skills?
- sage installs in Claude Code, and its skills also install in Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf with the skills CLI. Each skill's page has the install command. Flowy's auto-invocation, which fires a skill when your prompt matches, runs in Claude Code only.
Is this plugin yours?
Claim it with GitHubSubmit a pluginPromote it