PromptTrace offers free, browser-based interactive labs where users attack real large language models to practice prompt injection, RAG poisoning, tool misuse, and other LLM vulnerabilities. It includes Context Trace visualization of assembled prompts (with secrets redacted), a progressive Gauntlet of challenges, and learning modules aligned with OWASP Top 10 for LLM and Agentic Applications. No experience is required and all content is free.
In the LLM eval & observability space, Prompt Injection Labs takes a focused approach. It focuses on learning practical LLM security, prompt injection, and AI red-teaming skills through interactive, sandboxed exercises. Prompt Injection Labs is a consumer product aimed at security professionals and developers. It is available for free. Prompt Injection Labs is available on the web.
It is developed by Aired Labs, and it first shipped in 2025. Among its 6 catalogued features are Prompt Injection Labs, Context Trace, and RAG Poisoning. The interface is available in Arabic and English.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do