LLM Sec Review — Security agent for Claude Code
LLM/agent security review specialist — prompt injection, the Agents Rule of Two, tool-call authorization, model-output handling, secret isolation from model context, RAG poisoning, and abuse/cost cont.
How to install LLM Sec Review
Installs to ~/.claude/agents/ozanozcan-ai-wow-llm-sec-review.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/ozanozcan/ai-wow/HEAD/agents/llm-sec-review.md -o ~/.claude/agents/ozanozcan-ai-wow-llm-sec-review.md Restart Claude Code, or start a new session, for it to be picked up.
What LLM Sec Review does
name: llm-sec-review description: LLM/agent security review specialist — prompt injection, the Agents Rule of Two, tool-call authorization, model-output handling, secret isolation from model context, RAG poisoning, and abuse/cost controls. Use when a diff touches prompts, tool/function-calling, agent workflows, RAG/retrieval pipelines, MCP servers, or any endpoint that feeds user text to a model. For general application security (authz, injection, CSRF, secrets outside model context) use the
Alternatives in Security
- Malware Analyst — You are an elite malware analyst focused on defensive security research 31.9k ★
- GraphQL Audit — GraphQL API security specialist 812 ★
- Offensive Security Engineer — Red-team the verification engine 179 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Kavach LLM
KAVACH LLM/AI security specialist. Audits prompt injection (direct + indirect/RAG), jailbreak/persona/system-p
AI Redteam
Use PROACTIVELY for AI CTF challenges and LLM security challenges. Triggers on prompt injection, jailbreak, LL
AI Security Reviewer
Use this agent when reviewing AI-related code (prompts, agent loops, RAG systems, tool definitions, output han
Testing Red Team
💀 Use this agent for authorized application-layer offensive security testing - OWASP Top 10, authentication/a
Feos Security
FEOS security reviewer (read-only). Use in S3 to produce the STRIDE threat model and in S6/G4 to review code,
AI Eng Warden
AI Engineering review of code touching LLM interactions, prompt construction, context management, agent archit
Related Skills
LLM Security
AI/LLM agent security audit (OWASP GenAI/LLM Top 10 2026): prompt injection (direct + indirect/RAG), jailbreak
LLM
Security review of AI/LLM features — prompt injection, agent tool authority, RAG poisoning, and unsafe model o
Secure AI Customer Support Platform
Secure LLM-powered customer support platform: an AI agent (Claude) with grounded RAG answers, authorization-en
