Building a Security Scanner for LLM Apps
We're adding something new to Promptfoo's suite of AI security products: code scanning for LLM-related vulnerabilities. In this post, I will:
- Briefly introduce the new product
- Explain why we think engineering teams need a scanner focused exclusively on interactions with LLMs and agents
- Demonstrate the scanner in action on a few real-world CVEs (click here to skip the background and jump straight to real examples)