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.
Metrics
CVSS 3.1 8.1/10
CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:HAffected software
Source: the vendor's advisory (CNA). NVD analysis pending.
| Vendor | Product | Versions |
|---|---|---|
| Amazon | strands-agents-tools | < 0.8.5 |
References
Timeline
- Published
- Aug 25, 2026
- Last modified
- Aug 26, 2026
- NVD status
- Awaiting Analysis