Skip to content
Safety

One public-facing AI agent on AWS could read, rewrite, and delete every other agent in the region.

The DecoderIndependent reporting·
AI brief

Zenity Labs researchers found that a single publicly accessible AI agent on Amazon's Bedrock AgentCore could be used to take over every AgentCore agent in the same AWS account and region. The attack exploited an internal AWS interface for temporary cloud credentials.

Why it matters: It shows that one exposed agent can compromise all other agents within the same AWS account and region.

Written by AI from The Decoder's published text.

Background

From our own funding, model and news trackers, not from the source.

Source

“Zenity Labs researchers say a single publicly accessible AI agent on Amazon's Bedrock AgentCore was enough to take over every AgentCore agent in the same AWS account and region.”
The Decoder, 08 Oct 2026, 13:01.

Reporting from a publisher outside the organisation being covered.

Read original story ↗