Show HN: Npx LLM-safe-haven – harden your AI coding agent in 60 seconds

Category: security

Tags: ai-security, cli-tool, coding-agents, security-hardening, prompt-injection

Score: 6.8/10 (Innovation: 6, Technical: 6, Documentation: 8, Utility: 7)

LLM Safe Haven is a CLI tool that audits and hardens AI coding agents against security risks like prompt injection and secret leakage. It supports multiple popular agents with adjustable security levels, making it a practical and timely utility for solo developers using AI-assisted coding.

Target audience: developers, machine learning engineers, devops

Repository: https://github.com/pleasedodisturb/llm-safe-haven · JavaScript · MIT

View on Hacker News