bluzir

Radius — AI skill for Claude Code

AI community

AI agents run shell commands on your machine.

How to install Radius

This entry records only its repository, not the path inside it, so there is no exact command to give. Open bluzir/radius and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Radius does

AI agents run shell commands on your machine. One hallucination = rm -rf or leaked ~/.ssh. RADIUS intercepts every tool call and runs it through regex, path checks, and rate limits before it executes. Code, not prompts.

Alternatives in AI

Cl4r1t4s — LEAKED SYSTEM PROMPTS FOR CHATGPT, CLAUDE, GEMINI, GROK, PERPLEXITY, CURSOR, LOVABLE, REPLIT, AND MORE 47.2k ★
DontFeedTheAI — Transparent anonymization proxy for AI-assisted pentesting 654 ★
Browser Search — A skill for AI agents: search the web with SearXNG, browse with Camofox, bypass protections with CloakBrowser 499 ★

README

Draw the boundary.
No LLM in the decision loop.

"The more data & control you give to the AI agent: (A) the more it can help you AND (B) the more it can hurt you." — [Lex Fridman](https://x.com/lexfridman/status/2023573186496037044)

The problem

Your agent has root access to your machine. Your security layer is a system prompt that says "please be careful." Think about that for a second.

Intelligence is scaling. Access is scaling. Security is not. One bad prompt and your agent reads `~/.ssh/id_rsa` or runs `rm -rf /`. One malicious skill and your credentials are gone before you notice.

You could review every action manually, but then why have an agent?

Why this matters

Numbers from 78 validated research sources (114 analyzed), Feb 2026:


13.4%	Of 3,984 marketplace skills scanned, 534 had critical issues. 76 were confirmed malicious, with install-time scripts that stole credentials.
6 / 6	Researchers tested six coding agents for tool injection. All six gave up remote code execution through poisoned tool metadata.
85%+	A 78-study survey of prompt-based guardrails found most break under adaptive red-team attacks. The LLM can't reliably police i