AI Redteam — Security agent for Claude Code
Use PROACTIVELY for AI CTF challenges and LLM security challenges.
How to install AI Redteam
Installs to ~/.claude/agents/bilal-spotted-claude-code-ctf-rig-ai_redteam.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/bilal-spotted/claude-code-ctf-rig/HEAD/agents/ai_redteam.md -o ~/.claude/agents/bilal-spotted-claude-code-ctf-rig-ai_redteam.md Restart Claude Code, or start a new session, for it to be picked up.
What AI Redteam does
name: ai_redteam description: Use PROACTIVELY for AI CTF challenges and LLM security challenges. Triggers on prompt injection, jailbreak, LLM-guarded flags, system-prompt extraction, provided model files, RAG or agent exploitation, MCP tool poisoning, agentic tool abuse, AI-powered filter or WAF bypass, and vulnerable "vibe-coded" applications. model: opus
You are an AI red teaming specialist for the AI hacking CTF category. This category is newer and growing fast, attacks are creative
Alternatives in Security
- Security Requirement Extraction — Transform threat analysis into actionable security requirements 31.9k ★
- Claude Code System Prompts — by Piebald AI - All parts of Claude Code's system prompt, including builtin tool descriptions, sub agent promp 6.3k ★
- Patina Fidelity Auditor — Triggers to audit whether a patina rewrite preserved meaning versus the original text 352 ★
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
LLM Sec Review
LLM/agent security review specialist — prompt injection, the Agents Rule of Two, tool-call authorization, mode
Lens AI Security
AI security lens of the production readiness audit. Treats LLM and agent integrations as attack surface - prom
Security Lead
Use ONLY for authorized security work — pentesting engagements with written scope, CTF challenges, red-team ex
IoT Attacker
IoT and embedded systems security specialist. Handles firmware extraction and analysis, hardcoded credential d
Redteam Agent
Red Team penetration testing agent for HTB Expressway. Use when the user wants to attack or pentest the target
Related Skills
LLM Redteam
LLM red-team corpus runner — fires categorized prompt-injection / jailbreak / system-prompt-leak / data-exfil
Ctf Pwn
Solve pwn/binary exploitation CTF challenge: $ARGUMENTS
NLP Mir
Transformer-based NLP extraction pipeline achieving 95%+ accuracy on unstructured documents. Implements multi-