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

Summary

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. The affected products include Amazon

Lotu Radar provides attributed news summaries and links to the original publisher. Full reporting and copyright remain with the source.