Cloud HSM

Mentions · 7d0
Mentions · 30d0
All mentions1
First seenAug 18, 2026
Last mentionedAug 18, 2026

Timeline

1 articles · newest first

Google’s $10,000 refund test shows why AI agents need zero trust

Google released an open-source zero-trust reference architecture for AI agents defending against prompt injection via signed database writes, gVisor sandboxing, and deterministic gating.

Help Net SecurityAug 18, 00:00 UTC · Aug 18, 2026AI safety & security3 · 1 read

Appears with

Cloud KMSproduct · 1
Googleorganization · 1
Googlevendor · 1
gVisorproduct · 1
Geminiai model · 1
Agent Development Kitproduct · 1

Entities are extracted by the model from each article. First seen Aug 18, 2026, last mentioned Aug 18, 2026. Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.