feat(llm-security-copilot): port llm-security v5.1.0 to GitHub Copilot CLI

Full port of llm-security plugin for internal use on Windows with GitHub
Copilot CLI. Protocol translation layer (copilot-hook-runner.mjs)
normalizes Copilot camelCase I/O to Claude Code snake_case format — all
original hook scripts run unmodified.

- 8 hooks with protocol translation (stdin/stdout/exit code)
- 18 SKILL.md skills (Agent Skills Open Standard)
- 6 .agent.md agent definitions
- 20 scanners + 14 scanner lib modules (unchanged)
- 14 knowledge files (unchanged)
- 39 test files including copilot-port-verify.mjs (17 tests)
- Windows-ready: node:path, os.tmpdir(), process.execPath, no bash

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

README.md

@@ -40,6 +40,18 @@ Key commands: `/security posture`, `/security audit`, `/security scan`, `/securi
 
 ---
 
+### [LLM Security — Copilot CLI Port](plugins/llm-security-copilot/) `v5.1.0`
+
+Port of LLM Security for GitHub Copilot CLI. Same 8 hooks, 18 skills, 6 agents, 20 scanners, 14 knowledge files — all running on Windows, macOS, and Linux.
+
+A protocol translation layer (`copilot-hook-runner.mjs`) normalizes Copilot's camelCase I/O to Claude Code's snake_case format, so all original hook scripts run **unmodified**. Skills use the Agent Skills Open Standard (SKILL.md). Agents use Copilot's `.agent.md` format.
+
+Use case: internal verification of skills, MCP servers, repos, VS Code extensions, and other agentic AI projects from within Copilot CLI.
+
+→ [Full documentation](plugins/llm-security-copilot/README.md)
+
+---
+
 ### [Config-Audit](plugins/config-audit/) `v3.0.1`
 
 Configuration intelligence for Claude Code — health checks, feature discovery, and auto-fix.