News for hackers. Stuff that matters.
Re:Remote Prompt Injection in Gitlab Duo Leads to Source Cod... by Kholin on Monday May 26, 2025 @11:29PM (#44103723)
If Duo were a web application, then would properly setting the Content Security Policy (CSP) in the page response headers be enough to prevent these kinds of issues?

https://developer.mozilla.org/en-US/docs/Web/HTTP/Guides/CSP

Re:Remote Prompt Injection in Gitlab Duo Leads to Source Cod... by cutemonster on Tuesday May 27, 2025 @02:09AM (#44104317)
To stop exfiltration via images? Yes seems so? If you configure img-src:

  The first directive, default-src, tells the browser to load only resources that are same-origin with the document, unless other more specific directives set a different policy for other resource types.

  The second, img-src, tells the browser to load images that are same-origin or that are served from example.com.
But that wouldn't stop the AI from writing dangerous instructions in plain text to the human