aguara
Active·★ 94·Apache-2.0·Updated 2026-10-05
★ Trending★ Code Assistant★ Security & Safety
Aguara is a security scanner designed for AI agent skills and MCP servers, capable of detecting prompt injection, data exfiltration, and supply-chain attacks before deployment. It performs static analysis with a 4-layer engine and 173 detection rules without requiring API keys, cloud access, or LLMs.
#AI Security#Static Analysis#Prompt Injection#Data Exfiltration#Supply Chain Security#SAST#Go#Developer Tools
01
Features
01173 detection rules across 13 categories, including prompt injection, data exfiltration, and supply-chain attacks.
024-layer analysis engine combining pattern matching, NLP-based markdown analysis, taint tracking, and rug-pull detection.
03Confidence scoring for findings (0.0-1.0) and actionable remediation guidance.
04CI-ready with JSON, SARIF, and Markdown output formats, plus GitHub Action support.
05Supports scanning configurations from 17 MCP clients, including Claude Desktop, Cursor, and VS Code.
02
Compatibility
Go
Runtime
Verified via docs
Docker
Container Platform
Verified via docs
Homebrew
Package Manager
Verified via docs
macOS
Operating System
Verified via docs
Linux
Operating System
Verified via docs
Windows
Operating System
Verified via docs
03
Quick start
1
$ curl -fsSL https://raw.githubusercontent.com/garagon/aguara/main/install.sh | bash
04
Use cases
↳Pre-deployment security scanning of AI agent skills and MCP server configurations.
↳Continuous integration (CI) pipelines for automated security checks on code changes.
↳Auditing and discovery of existing MCP client configurations and potential threats on a machine.
↳Custom rule creation in YAML for project-specific security requirements.
↳Embedding the scanner as a Go library within other tools, like Aguara MCP.
05
Alternatives
Comments
Log in to leave a comment
No comments yet. Be the first!