tirith
Terminal security tool that intercepts malicious behaviors such as homograph URLs, pipe injection, and ANSI injection.
- Type
- Agent Skill
- Open source
- Yes
- GitHub Stars
- ★ 2.5k
- Source
- skill-github
- Repository
- github.com/sheeki03/tirith
Overview
tirith is a terminal security tool designed for developers and AI agents. It intercepts homograph URLs, pipe-to-shell injection, ANSI injection, obfuscated payloads, data leaks, and malicious AI skills/configurations before execution. With simple installation and activation steps, tirith protects your terminal from various attacks. Ideal for developers and AI agents that need to run commands in terminal environments.
Capabilities
- ▪Intercept homograph URLs
- ▪Block pipe-to-shell injection
- ▪Defend against ANSI injection
- ▪Detect obfuscated payloads
- ▪Prevent data leakage
- ▪Scan for malicious AI skills/configurations
Use cases
Setup
brew install tirith; eval "$(tirith init)"
This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.
FAQ
How does tirith work?
tirith intercepts and checks for potential malicious behavior before command execution.
Which operating systems are supported?
Supports macOS, Linux, and Windows.
Related skills
gemini-cli
Gemini CLI is an open-source AI agent that brings Gemini's powerful capabilities directly into the terminal.
private-gpt
Provides a complete API layer for local models, supporting RAG, skills, tools, and more.
planning-with-files
File-based persistent planning skill, ideal for AI coding agents and long-running tasks.
scientific-agent-skills
Transform any AI agent into a scientific assistant with 147 ready-to-use research skills.
susi_alexa_skill
A skill that enables question-and-answer interactions between Alexa and Susi AI.
claude-context
Provides code search capabilities for Claude Code, turning the entire codebase into context.