Prompt injection
Prompt injection
Posted Aug 5, 2026 8:20 UTC (Wed) by njh (subscriber, #4425)In reply to: Prompt injection by marcH
Parent article: An LLM agent attempts to compromise a project on GitHub
> What/where is the border between prompt and "not-prompt"? What is "not-prompt" in this particular context?
Instructions addressed to an LLM embedded in documents that the LLM is operating upon as data. Person A gives a prompt like "please summarise document X for me" and the LLM potentially *acts* on prompt-like instructions in document X, which was written by someone other than Person A.