11 points | by fogeltine 14 hours ago
5 comments
I wonder how many other AI coding tools have similar assumptions baked into their security model.
[flagged]
the interesting part isn't the escape itself, it's all the trusted software that unknowingly helps it :O
Amazing
this is a good reminder that 'sandboxed' doesn't necessarily mean 'safe.'
I wonder how many other AI coding tools have similar assumptions baked into their security model.
[flagged]
the interesting part isn't the escape itself, it's all the trusted software that unknowingly helps it :O
Amazing
this is a good reminder that 'sandboxed' doesn't necessarily mean 'safe.'