All activity
Anthony D'Onofrioleft a comment
Hey Product Hunt 👋 I'm Anthony — security consultant, PhD, eCPPT. There's a real gap between "everyone is shipping LLM agents" and "almost no one has hands-on experience breaking one." Most training in this space is either a blog post or a static CTF with a hardcoded flag. I wanted something different. Wraith Academy is my attempt at that. It's free, fully hands-on in the browser, and every...
Wraith AcademyLearn AI pentesting by attacking real LLM agents
Free hands-on CTFs where you attack live LLM agents: prompt injection, tool abuse, RAG poisoning, and more. Built for security pros and AI engineers who want to understand how AI systems actually break, not just read about it.
Wraith AcademyLearn AI pentesting by attacking real LLM agents
Anthony D'Onofriostarted a discussion
What's the weakest part of AI agent security right now?
Curious what the PH community thinks. There's a lot of noise about LLM safety, but "safety" and "security" get conflated constantly, and the actual attack surface on an agent in production is its own thing. From where I sit, the most under-addressed failure modes seem to be: Indirect prompt injection via retrieved content (RAG sources, tool outputs, even user-uploaded docs) Tool/function abuse...