A company implements a generative AI chatbot for customer service. Users discover they can override the chatbot's safety guidelines by embedding instructions in customer support tickets. What attack vector does this represent?
Select an answer to reveal the explanation.
Short Explanation and Infographic
Here's the deal — b is correct because indirect prompt injection occurs when attacker-controlled content (such as text in customer tickets) is processed by the LLM and overrides its original instructions. This is distinct from direct prompt injection because the attack vector is through legitimate-seeming input data.
Full explanation below image
Full Explanation
B is correct because indirect prompt injection occurs when attacker-controlled content (such as text in customer tickets) is processed by the LLM and overrides its original instructions. This is distinct from direct prompt injection because the attack vector is through legitimate-seeming input data. Data poisoning (A) affects training, not inference. Model extraction (C) aims to replicate the model. Membership inference (D) targets training data recovery.