Good question -- I have been pointing claude at repos for security reviews before I install stuff now for exactly this reason.

▲

ShinyLeftPad 4 hours ago | parent [-]

It's so funny to read these, as if countless examples didn't prove that llms don't actually distinguish between your instructions and the data they read at your request.

Do you think a malicious repo author won't think of hiding a suitable prompt within?

	▲	NavinF 4 hours ago \| parent [-]
		> countless examples Show me just one where a frontier model got prompt injected when checking if code if malicious. FWIW I can do this, but I bet you can't.