News for hackers. Stuff that matters.
Re:Claude Cowork Exfiltrates Files by alienbaby on Wednesday January 14, 2026 @05:55PM (#46625096)
The best I've heard is rewriting prompts as summaries before forwarding them to the underlying ai, but has it's own obvious shortcomings, and it's still possible. If harder. To get injection to work
Re:Claude Cowork Exfiltrates Files by groby_b on Thursday January 15, 2026 @08:24AM (#46632130)
Alas, the summarizer... is vulnerable to prompt injection.