Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

> prompt injection appears to be largely solved already.

I trust Anthropic's research, and Opus-5 is definitely the most robust model against prompt injection. However, in my experiments - only one specific scenario - this was still possible [1][2].

[1] https://itmeetsot.eu/posts/2026-07-27-opus5/

[2] https://itmeetsot.eu/posts/2026-08-12-opus5_automode/



That was a great read!

Does the star trek theme help in the injection? Do other topics work just as well?

Does it work with a normal prompt instead of /init?


Thanks!

I think other topics may work as well (I tried a math challenge too). It also works with a prompt like "Summarize this repo".

In general, there are almost infinite possibilities for the prompt injection payloads, it's a matter of creativity and trial and error.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: