Awarexone

LLM Redteam — Data skill for Claude Code

Data community

LLM red-team corpus runner — fires categorized prompt-injection / jailbreak / system-prompt-leak / data-exfil / indirect-injection / guardrail-bypass payloads at a chat endpoint and canary-detects whi.

How to install LLM Redteam

Installs to ~/.claude/skills/awarexone-agentic-bug-hunter-llm-redteam/SKILL.md

Terminal

mkdir -p ~/.claude/skills/awarexone-agentic-bug-hunter-llm-redteam && curl -fsSL https://raw.githubusercontent.com/Awarexone/Agentic-Bug-Hunter/HEAD/commands/llm-redteam.md -o ~/.claude/skills/awarexone-agentic-bug-hunter-llm-redteam/SKILL.md

Restart Claude Code, or start a new session, for it to be picked up.

What LLM Redteam does

description: LLM red-team corpus runner — fires categorized prompt-injection / jailbreak / system-prompt-leak / data-exfil / indirect-injection / guardrail-bypass payloads at a chat endpoint and canary-detects which land. Usage: /llm-redteam --url --field message [--category jailbreak]

/llm-redteam

Automated LLM/agentic red-teaming. Instead of hand-firing one prompt-injection at a time, this runs a categorized corpus against a chat endpoint and uses a **canary token**

Alternatives in Data

Claude Code Memory Setup — Up to 71.5x fewer tokens per session on Claude Code with Obsidian + Graphify 947 ★
Vibesec — Helps write secure code by preventing common vulnerabilities including IDOR, XSS, SQL injection, SSRF, and wea 687 ★
AI Data Extractor — Free open-source extractor for AI coding assistant chat histories 544 ★