1 / 70 · 07 Security Testing for AI Apps · Prompt Injection: The SQL Injection of AI⊞ allnext →☰ Read as one page
1.1LLM01: Prompt Injection
Prompt injection is the most critical vulnerability in LLM applications. An attacker manipulates the LLM by crafting input that overrides or subverts the system prompt, causing the model to perform unintended actions. It is to AI applications what SQL injection was to web applications in the 2000s -- pervasive, dangerous, and not yet fully solved.