CVE-2026-78379

Description

Improper neutralization of input used for LLM prompting in the python_repl tool in Amazon Strands Agents Tools before 0.8.5 might allow remote actors to execute arbitrary Python code on the agent's host by bypassing the human consent gate, via a crafted prompt that forwards non_interactive_mode as a keyword argument through the batch tool. To remediate this issue, users should upgrade to version 0.8.5 or later.

CVSS Vector

References

• https://aws.amazon.com/security/security-bulletins/2026-089-aws/
• https://pypi.org/project/strands-agents-tools/0.8.5/