Agents
[TBD]
Outcome
- [TBD]
Metrics
- [TBD]
Tools & Resources
- Gandalf - An AI agent for you to practice prompt injection (Free)
- agentic-radar - A security scanner for your LLM agentic workflows(Free)
- Language Model Security Database - Database enumerating different ways of exploiting LLMs (Free)
- damn-vulnerable-llm-agent (Free)
- Llama Firewall - The framework to detect and mitigate AI centric security risks (Free)
- Rebuff AI - A tool to detect prompt injections (Free)
- LLM Guard (Free)