Re:Agent Reading Test
by throwatdem12311 on Monday April 06, 2026 @07:56PM
(#47668977)
What a great target for someone to hack and add some secret prompt injections into.
[ Parent
| on HN ]
Hah, I actually originally had some stuff in the site that Claude Code's summarization agent (presumably Haiku) thought was prompt injection, and refused to give content to the foreground agent I was working with. I had to remove some stuff from the site to work around that. Of course implementation will vary and not all platforms have the same safety stuff in place around this yet, so there's probably some interesting stuff to do there.
Re:Agent Reading Test
by lorenzohess on Tuesday April 07, 2026 @12:17AM
(#47670699)
Ideally the website would emphasize self hosting the code and analyzing it before running