LLM SecRange: Open-Source Penetration Testing Playground for Large Language Models & Vulnerable Agents
github.com | tool | #ai-security | #rce | #ctf | #prompt-injection | #red-team | #llm-security | #owasp-llm-top-10 | #vulnerable-agent | #training-range
Summary
LLM SecRange is a Flask-based local LLM security training range featuring 8 prompt-injection CTF levels, OWASP LLM Top 10 (2025) labs, and a vulnerable ReAct bank agent with switchable target models.
Why it matters
Offers security researchers and penetration testers an out-of-the-box, comprehensive environment to practice prompt injection, OWASP LLM Top 10 risks, and agent tool-abuse exploitation against real models.
- Published
- Collected
--- id: 7528 title: "LLM SecRange: Open-Source Penetration Testing Playground for Large Language Models & Vulnerable Agents" source_domain: github.com source_url: "https://github.com/gatsby-sec/llm-sec-range" published_at: "2026-06-20T08:06:45Z" tags: ["ai-security", "rce", "ctf", "prompt-injection", "red-team", "llm-security", "owasp-llm-top-10", "vulnerable-agent", "training-range"] phying_url: "https://phying.com/item/7528" lang: en --- # LLM SecRange: Open-Source Penetration Testing Playground for Large Language Models & Vulnerable Agents ## Summary LLM SecRange is a Flask-based local LLM security training range featuring 8 prompt-injection CTF levels, OWASP LLM Top 10 (2025) labs, and a vulnerable ReAct bank agent with switchable target models. ## Why it matters Offers security researchers and penetration testers an out-of-the-box, comprehensive environment to practice prompt injection, OWASP LLM Top 10 risks, and agent tool-abuse exploitation against real models. ## Intelligence Metadata - **Sources:** github.com - **Published:** 2026-06-20T08:06:45Z - **Original:** https://github.com/gatsby-sec/llm-sec-range - **Phying News:** https://phying.com/item/7528