# Ask Security Sentinel

> Pre-flight security checker. Scan for secrets and vulnerabilities.

- Skill: `navanithans/ask-security-sentinel` (Agent Skill, multi-file: 5 files)
- Install (CLI): `npx skillmds@latest add navanithans/ask-security-sentinel`
- Raw SKILL.md: https://api.skillmd.com/api/skills/navanithans/ask-security-sentinel/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Security
- Author: NavanithanS (https://skillmd.com/u/navanithans)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/navanithans/ask-security-sentinel

---


<critical_constraints>
✅ MUST run before git commit or deploy
✅ MUST halt and warn if secrets found
✅ MUST enforce parameterized queries
</critical_constraints>

<secret_patterns>
- `sk_live_...` (Stripe)
- `ghp_...` (GitHub)
- `ey...` (JWT tokens)
→ If found: HALT, warn user, move to .env
</secret_patterns>

<vulnerability_checks>
## SQL Injection
❌ Bad: `DB::select("SELECT * FROM users WHERE id = $id")`
✅ Good: `DB::select("...", [$id])`

## XSS
- Check for `{!! $variable !!}` in Blade
- Ensure user explicitly confirmed safe HTML
</vulnerability_checks>