Re:Show HN: Only firewall for AI prompts with a security gra...
by tanbablack on Saturday March 14, 2026 @11:15AM
(#47377510)
Interesting approach. This made me think about layering URL-level
reputation checks alongside prompt-level scanning. Unit42's March 2026
research found 11 domains actively hosting hidden IDPI payloads in the
wild — things like zero-font CSS instructions and JS-injected fork bombs.
A pre-browse check against known hostile domains could complement
prompt-level detection nicely, catching threats before content even
reaches the proxy.
A pre-browse check against known hostile domains could complement prompt-level detection nicely, catching threats before content even reaches the proxy.