CVE-2026-78379 - Consent bypass in Strands Agents Tools python_repl tool

Summary

CVE-2026-78379 is a consent bypass in the python_repl tool of the strands-agents-tools package, used with the Strands Agents Python SDK, in versions before 0.8.5. A crafted prompt can forward non_interactive_mode as a keyword argument through the batch tool, skipping the operator approval gate. Remote actors can then execute arbitrary Python code on the agent's host.

Mitigation

Fixed in 0.8.5 or later. Upgrade strands-agents-tools to version 0.8.5 or newer.

Related items

• HighCVE-2026-115413 - AWS API MCP Server OAuth token audience validation bypassSame vendor · AWS Security Bulletins
• MediumCVE-2026-116635 - Improper limitation of a pathname to a restricted directory in the deployment status component of the AWS Serverless MCP ServerSame vendor · AWS Security Bulletins
• MediumCVE-2026-120497 - Stored cross-site scripting in the HTML report generator of aidlc-traceability in AWS AI-DLC WorkflowsSame vendor · AWS Security Bulletins
• HighCVE-2026-115415 - Secret masking bypass in the environment tool in Strands Agents ToolsSame vendor · AWS Security Bulletins
• HighGHSA-4v6f-7vjh-6x4m: Strands Agents SDK: Exposure of data element to wrong session in the A2A ServerSame vendor · GitHub Advisory Database