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>

plugins/llm-security-copilot/skills/pre-deploy/SKILL.md

@@ -0,0 +1,38 @@
+---
+name: security-pre-deploy
+description: Pre-deployment security checklist — verify controls, compliance, and production readiness
+---
+
+# Pre-Deploy Checklist
+
+10 automated checks + 3 manual verification questions.
+
+## Automated Checks (PASS/FAIL/WARN/N-A)
+
+Perform these checks using Read, Glob, and Grep:
+
+1. **Deny-first permissions** — Settings contain restrictive default permissions
+2. **Secrets hook active** — pre-edit-secrets hook is registered and script exists
+3. **Path guard active** — pre-write-pathguard hook is registered and script exists
+4. **Destructive command guard** — pre-bash-destructive hook registered and script exists
+5. **MCP servers verified** — All configured MCP servers have been audited
+6. **No hardcoded secrets** — Grep for API keys, tokens, passwords in source files
+7. **Gitignore covers secrets** — .gitignore includes .env, credentials, keys
+8. **Security instructions present** — CLAUDE.md or copilot-instructions.md has security section
+9. **Sandbox enabled** — No `dangerouslySkipPermissions` or bypass flags
+10. **Audit logging** — Post-tool hooks are active for monitoring
+
+## Manual Verification
+
+Ask the user these questions:
+1. "Is this running on an Enterprise plan with audit logging?"
+2. "Has a Data Protection Impact Assessment (DPIA) been completed?"
+3. "Is there an incident response plan for AI security events?"
+
+## Report
+
+Present as checklist table. Verdict by pass count:
+- 10/10: Low risk — Ready to deploy
+- 7-9: Medium risk — Address gaps first
+- 4-6: High risk — Significant exposure
+- 0-3: Extreme risk — Do not deploy