# AI Security Review

> Activate when the user asks to audit, review, scan, or assess the security of an AI application, agent, chatbot, or LLM-powered system. Also activate when the user mentions prompt injection, data exfiltration, guardrail bypass, red-teaming, AI SBOM, cognitive policy, OWASP LLM Top 10, NIST AI RMF, or EU AI Act compliance.

## Facts
- Page: https://tashan.sh/capability/skill-nuguardai-ai-security-review
- tashan id: skill:NuGuardAI/ai-security-review
- Source: https://github.com/NuGuardAI/nuguard
- Type: skill
- Category: security
- tashan score: not scored (catalogued only — too little public evidence)
- Adoption: 9.0
- Upkeep: 98.0
- Freshness: 95.0
- Evidence coverage: 84% of the inputs this score can use
- Health: active
- Instruction depth: not yet graded
- License: NOASSERTION
- Official: no

## Install

```sh
cp -r ai-security-review ~/.claude/skills/
```

## Security audit
Not scanned. We audit npm-published capabilities; this one has no npm package we can resolve, or has not reached the queue. This is not a clean bill of health.

---
Measured 2026-09-12 by tashan (https://tashan.sh) from public evidence. Scorer s5.