CVE-2026-78379 Details
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 4.0 Severity and Vector Strings:
CVSS 3.x Severity and Vector Strings:
No data available for CVSS Version 2.0 on this CVE.
CISA-ADP
Assessed Aug 25, 2026References to Advisories, Solutions, and Tools
By selecting these links, you will be leaving this site. These are references gathered from the official CVE record and are not endorsed by Volerion.
| URL | Source(s) | Tag(s) |
|---|---|---|
| https://aws.amazon.com/security/security-bulletins/2026-089-aws/ | AMZN | |
| https://pypi.org/project/strands-agents-tools/0.8.5/ | AMZN |
Weakness Enumeration
No weakness enumeration is available for this CVE.
Affected Products
No affected product data is available for this CVE.
Change History
2 change records found show changes
| Date | Action | Recorded By |
|---|---|---|
| Aug 25, 2026 | CVE Modified | CISA-ADP |
| Aug 25, 2026 | New CVE Received | AMZN |