A security researcher demonstrates that by prefixing inputs to a customer service chatbot with 'Ignore previous instructions and instead...', the chatbot reveals its system prompt. What vulnerability does this exploit?
Select an answer to reveal the explanation.
Short Explanation
Here's the deal — you're seeing prompt injection because the chatbot can't reliably separate user input from its system instructions. That lets crafted text override the prompt and leak confidential instructions.
Full Explanation
Prompt injection is correct because it exploits the LLM's inability to reliably distinguish user inputs from system instructions. An attacker can craft inputs that override system prompts, extract confidential instructions, or cause unintended behaviors. The SQL injection in the chatbot's database backend is wrong because it is a database attack unrelated to LLMs. The cross-site scripting in the chatbot's web interface is wrong because it is a web application vulnerability. The API key leakage through response headers is wrong because it is an infrastructure security issue.