I don't know. You can poison a prompt with less than <1% of its input or RAG-Tok...

		Helmut10001 7 days ago \| parent \| context \| favorite \| on: An agent used DNS to reach an external chatbot I don't know. You can poison a prompt with less than <1% of its input or RAG-Token-Content. Anything that the Agents retrieved or viewed could have included instructions that they misinterpreted allowing them to hack into something.
		help