THE PERMISSION [LAYER]

AI agent incident

An agentic threat actor called JadePuffer allegedly wiped an Azure tenant using exposed credentials

Reported · 1 source

  • credential-theft
  • autonomous-attack

What happened

Dark Reading reported that JadePuffer, which it described as an agentic threat actor, allegedly used exposed credentials to get into an Azure tenant and delete its cloud storage, applications and databases.

Why it matters

There was no exploit. Exposed credentials got the actor in and the deletions followed, which puts credential hygiene ahead of any defense against novel AI attacks. Keep the hedge too: one outlet so far, and it says allegedly.

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. Dark Reading JadePuffer AI Actor Compromises Azure Tenant in Destructive Cloud Attack

Background reading

What is agent identity? An explainer on the problem behind this incident.

Cite or correct this record

“An agentic threat actor called JadePuffer allegedly wiped an Azure tenant using exposed credentials.” The Permission Layer AI Agent Incident Database, https://thepermissionlayer.com/incidents/jadepuffer-azure-tenant-destruction/. 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.