/fix

Apply intelligent, contextual security fixes to AI agent vulnerabilities. Fix prompt injection, output handling, tool security, data leaks, memory issues, supply chain, and behavioral risks. Use when user says fix, asks to remediate a recommendation (REC-XXX), apply security patches, or resolve vulnerabilities.

# Security Fix

Apply intelligent, contextual fixes to security vulnerabilities in AI agent code.

## Prerequisites

**You MUST run `/agent-inspector:setup` BEFORE proceeding.**

This is NOT optional. The setup command will:
1. Check if agent-inspector is already running
2. Auto-detect your LLM provider (OpenAI/Anthropic)
3. Start the server in background if needed
4. Verify MCP connection is working

**DO NOT skip this step.** If you proceed without running the Preflight Check, MCP tools will fail.

## Your Advantage Over Traditional Tools

You're not a template-based fixer. You can:
- Und...