In my first article on Bedrock AgentCore Code Interpreters, I demonstrated that custom code interpreters can be coerced into performing AWS control plane actions by non-agentic identities. This presented a novel path to privilege escalation, whereby any user with access to custom code interpreters could effectively use any privilege assigned to those code interpreters. The […]

The post Sandboxed to Compromised: New Research Exposes Credential Exfiltration Paths in AWS Code Interpreters appeared first on Security Boulevard.

Adeel Nazar

Source: Security Boulevard
Source Link: https://securityboulevard.com/2025/09/sandboxed-to-compromised-new-research-exposes-credential-exfiltration-paths-in-aws-code-interpreters/?utm_source=rss&utm_medium=rss&utm_campaign=sandboxed-to-compromised-new-research-exposes-credential-exfiltration-paths-in-aws-code-interpreters