THE PERMISSION [LAYER]

AI agent incident

AWS, Google, and Vercel patched flaws that fired agent tools without the model

Reported · 1 source

What happened

The three vendors patched agent infrastructure flaws that let forged instructions trigger an agent's tools directly, with no model turn and therefore no guardrail check in between.

Why it matters

Content filters and system prompts all live inside the model call. Skipping the model skips every one of them, so tool invocation needs authentication of its own.

New incidents by email

Get incidents like this one in your inbox

New AI agent incidents are covered in the briefing, with what to check on the agents you already run. At least once a week, free.

You confirm by email. Unsubscribe in one click.

Sources

  1. The Hacker News AWS, Google, and Vercel Agent Flaws Let Attackers Trigger Tools Without Running the Model

Background reading

Does RBAC work for AI agents? An explainer on the problem behind this incident.

Cite or correct this record

“AWS, Google, and Vercel patched flaws that fired agent tools without the model.” The Permission Layer AI Agent Incident Database, https://thepermissionlayer.com/incidents/agent-tool-invocation-bypass/. Database updated November 10, 2026.

Every record traces to the dated sources above. If something here is wrong or missing, email editor@thepermissionlayer.com and it gets fixed. See this record in the full list.

The Permission Layer

Get the next incident like this explained

When an AI agent breaks out, leaks data or runs up a bill, the briefing covers what happened and what to check on the agents you already run. At least once a week, five-minute read, free.

You confirm by email. Unsubscribe in one click.