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.
Affected products
| Vendor | Product | Affected | Fixed |
|---|---|---|---|
| Amazon | strands-agents-tools | < 0.8.5 | 0.8.5 |
References
- https://pypi.org/project/strands-agents-tools/0.8.5/ patch release-notes
- https://aws.amazon.com/security/security-bulletins/2026-089-aws/ vendor-advisory