passdrill
AI & LLM Engineering · Evaluation, Testing & Safety · Card 006/010 hard

A team building an agent finds two different attack patterns during security testing: in one, a user of the application directly crafts an unusual prompt trying to get the agent to ignore its instructions; in the other, a trusted user asks the agent to summarize a webpage, and the webpage's own text contains hidden instructions trying to redirect the agent. Using the threat-model distinction drawn in Anthropic's guidance for mitigating these attacks, how are the two cases distinguished?

  1. Both are the same attack, jailbreaking, because in both cases the ultimate effect is that the agent's system prompt is overridden, regardless of who supplied the adversarial text
  2. The first is a direct prompt injection (or jailbreak), where the application's own user is the adversary crafting the input; the second is an indirect prompt injection, where the user is trusted but the agent processes third-party content -- such as a webpage, email, or tool result -- that itself contains adversarial instructions
  3. The first is indirect prompt injection, because the user's prompt is only indirectly related to the agent's task, while the second is direct prompt injection, because the webpage content directly reaches the model
  4. The first is a data poisoning attack, because it targets the model's training data, while the second is a prompt injection attack, because it targets the model's inference-time input
Next card → Shuffle