LLM AI Hunter — Data & AI agent for Claude Code
LLM and Agentic AI vulnerability specialist.
How to install LLM AI Hunter
Installs to ~/.claude/agents/h-mmer-pentest-agents-llm-ai-hunter.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/H-mmer/pentest-agents/HEAD/.claude/agents/llm-ai-hunter.md -o ~/.claude/agents/h-mmer-pentest-agents-llm-ai-hunter.md Restart Claude Code, or start a new session, for it to be picked up.
What LLM AI Hunter does
name: llm-ai-hunter description: "LLM and Agentic AI vulnerability specialist. Covers OWASP LLM Top 10 v2025 (LLM01-LLM10) and OWASP Agentic AI Top 10 (AA-01..AA-10). Dispatcher passes subtype — 'prompt-injection', 'indirect-injection', 'tool-abuse', 'rag-poisoning', 'vector-idor', 'mcp', 'model-server', 'output-handling', or 'ascii-smuggling' — in the task; falls back to inference. Use when a target ships a chatbot, RAG / search-over-docs, AI assistant, MCP server, agentic tool-use plugin,
Alternatives in Data & AI
- Credential Hunter — Autonomous credential-attack pipeline runner 4.5k ★
- LLM Expert — Use this agent for AI SDK integration, LLM provider configuration, prompt template management, error handling 434 ★
- Claude Code Agentic RAG Series — Planning docs and PRDs for the Claude Code Agentic RAG Masterclass video series 97 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Marketing Competitor Analyst
Use when the user wants competitive marketing research for a product/brand — building a database of top compet
Vercel AI SDK Expert
Use for Vercel AI SDK v5 implementation work: chat interfaces, tool calling, streaming, agentic loop control,
AI Adversarial Testing
AI Adversarial Testing Agent (SP 800-218A PW.8). Read-only w.r.t. product code. Exercises AI-specific attack p
Bug Hunter
Bug detection specialist. Finds logic errors, null pointers, boundary issues, race conditions, resource leaks,
Sqli Hunter
Active SQL injection hunter for an ingested program. Consumes webvuln-surface injection points + auth-context,
AI LLM Engineer
Use this agent when the user types /ai or asks for ai/llm engineer work — e.g., build a RAG pipeline over our
Related Skills
LLM Security
AI/LLM agent security audit (OWASP GenAI/LLM Top 10 2026): prompt injection (direct + indirect/RAG), jailbreak
Skill Lint
Security scanner for Claude Code / agent skills. Catches prompt injection, obfuscation, credential exfiltratio
LLM Redteam
LLM red-team corpus runner — fires categorized prompt-injection / jailbreak / system-prompt-leak / data-exfil