I'm sure this one probably isn't, but I have no clue how I would know whether it is without reviewing the source code myself (or pointing an agent at it etc)
Do you think a malicious repo author won't think of hiding a suitable prompt within?
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.
took me about 30 seconds to find. there's tons of them. of course it's an arms race, the models get better the harnesses get better the attackers get better but again: for the model itself, your prompt and third party data it reads are the same thing (input). as long as it is true, the attack will always be possible.
2. Nobody uses antigravity
3. That's not a prompt injection! That user prompt literally tells the LLM to follow a guide on the web. The guide says "do bad stuff" which the LLM does, just as the user asked. It would be a prompt injection if the prompt asked the LLM to analyze the guide, but that's obviously not what it asked
That's what I wrote