> Would you ever put a plain password (...)
Your comment bears no resemblance with the topic. The attack described in the article consists of injecting a malicious prompt in a way that the target's agent will apply it.
Your comment bears no resemblance with the topic. The attack described in the article consists of injecting a malicious prompt in a way that the target's agent will apply it.
The exploit involves random third parties sneaking in their own prompts in a way that leads a LLM to run them on behalf of the repo's owner. This exploit can be used to leak protected information. This is pretty straight forward and easy to follow and understand.