News for hackers. Stuff that matters.
Re:OpenCode Browse by eatfish on Tuesday November 17, 2026 @04:20AM (#50529221)
I keep asking my own agents if prompt injection is a solved problem. By and large the answer seems to be ‘no, anything a model sees can be used to steer it and enters the context’.

I know you can forward raw output through subagents to summarize content and mitigate the risk - but most projects don’t do that.

So why would anyone risk browser or email to agents where your secrets are at their most vulnerable. Serious question, looking for someone who knows this stuff and can reassure me (or not) on the real risks.

Re:OpenCode Browse by circularfoyers on Tuesday November 17, 2026 @04:29AM (#50529288)
Annoyingly the engineers in my team just argue it's not a risk because they have haven't witnessed it themselves or know anyone personally that have.
Re:OpenCode Browse by phrotoma on Tuesday November 17, 2026 @06:25AM (#50530022)
A friend who works in infosec was absolutely floored when I asked him how he was sandboxing the agents he runs on his main laptop. I guesss I'm finished being surprised but god damn.