Comment on Comet AI browser can get prompt injected from any site, drain your bank account
jrandomhacker@beehaw.org 2 weeks agoLLMs fundamentally don’t/can’t have “sanitized” or “unsanitized” content - it’s all just tokens in the end. “Prompt Injection” is even a bit too generous of a term, I think.
businessfish@lemmy.blahaj.zone 2 weeks ago
sure but one would hope that if the agent is interpreting content from the web as instructions that there would be literally any security measure between the webpage and the agent - whether that’s some input sanitization, explicit user confirmation, or prohibiting the agent from interpreting web pages as instructions at all.