this post was submitted on 12 Jun 2023
37 points (97.4% liked)

Programming

17299 readers
665 users here now

Welcome to the main community in programming.dev! Feel free to post anything relating to programming here!

Cross posting is strongly encouraged in the instance. If you feel your post or another person's post makes sense in another community cross post into it.

Hope you enjoy the instance!

Rules

Rules

  • Follow the programming.dev instance rules
  • Keep content related to programming in some way
  • If you're posting long videos try to add in some form of tldr for those who don't want to watch videos

Wormhole

Follow the wormhole through a path of communities [email protected]



founded 1 year ago
MODERATORS
 

From https://twitter.com/llm_sec/status/1667573374426701824

  1. People ask LLMs to write code
  2. LLMs recommend imports that don't actually exist
  3. Attackers work out what these imports' names are, and create & upload them with malicious payloads
  4. People using LLM-written code then auto-add malware themselves
you are viewing a single comment's thread
view the rest of the comments
[–] [email protected] 5 points 1 year ago

Indirect prompt injections will make this worse. Plugins lead to scraping insecure websites (i.e., search for docs for a particular topic). This can result in malicious context being embedded and suggested during a PR or code output.

That along with the above, faking commonly recommended inputs, it becomes very difficult to just trust and use LLM output. One argument is that experienced devs can catch this, but security is often about the weakest link, one junior dev's mistake with this could lead to a hole.

There are guard rails to put in place for some of these things (i.e., audit new libraries, only scrape from 'reliable' websites), but I suspect most enterprises/startups implementing this stuff don't have such guard rails in place.

Related