alt Hacker News> The issue title was interpolated directly into Claude's prompt via ${{ github.event.issue.title }} without sanitisation.
It's astonishing that AI companies don't know about SQL injection attacks and how a prompt requires the same safeguards.
Replies
arjvik • yesterday at 7:11 PM
There’s a known fix for SQL injection and no such known fix for prompt injection
rawling • yesterday at 7:11 PM
But you can't, can you? Everything just goes into the context...
➕ show 1 reply
No such mitigation exists for LLMs because they do not and (as far as anybody knows) cannot distinguish input from data. It's all one big blob