> What’s to stop an attacker from using prompt injection against this firewall? ... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		quinnjh 3 months ago \| parent \| context \| favorite \| on: Show HN: MCP Defender – OSS AI Firewall for Protec... > What’s to stop an attacker from using prompt injection against this firewall? Clearly you need a firewall-firewall. ..defense in depth?

gsundeep 3 months ago [–]

We'll soon be adding the ability to have multiple models perform the scan in parallel, so any attack would have to bypass all of the models.

superb_dev 3 months ago | [–]

So literally a firewall-firewall?

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact