Skip to content
archivevulnerability · 06 Aug 2026 · 08:57 UTC

AWS, Google, and Vercel Agent Flaws Let Attackers Trigger Tools Without Running the Model

last 60 dispatches · spectrum

Security flaws in agent infrastructure from Amazon Web Services (AWS), Google, and Vercel let untrusted or forged instructions reach an agent's tools with no check that a model turn had authorized them. In several of the attack paths, the model never ran at all, so system prompts, content filters, and model-level guardrails never got a chance to intervene. …

grounded ✓primary source ↗
Early access

Get the next one first.

Early access opens the actor API and MCP server first, plus alerts when an adversary you follow lands on the wire. One email when it's ready. Nothing else, ever.

bot-protected