Description (CNA)
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 (CNA)
| Vendor / product | Versions |
|---|---|
| Amazon / strands-agents-tools | affected 0 before 0.8.5 |
CWE
CWE-1427
References
- https://pypi.org/project/strands-agents-tools/0.8.5/
- https://aws.amazon.com/security/security-bulletins/2026-089-aws/
ADP enrichment
No English description supplied.
No references supplied.