About data exfiltration from Slack AI through indirect prompt injection.
Has this happened?
Yes 17 (13%)Not sure 23 (18%)No 88 (69%)
Votes cast 1–2 October 2026: 100,590 votes from 9,694 people.
Hacker News has set AI a lot of challenges over the years. Which ones has it met?
About data exfiltration from Slack AI through indirect prompt injection.
Votes cast 1–2 October 2026: 100,590 votes from 9,694 people.
Are companies really just YOLOing and plugging LLMs into everything knowing prompt injection is possible? This is insanity. We're supposedly on the cusp of a "revolution" and almost 2 years on from GPT-3 we still can't get LLMs to distinguish trusted and untrusted input...?