CVE-2026-78379
Consent bypass in python_repl tool via batch kwargs forwarding in Amazon Strands Agents Tools
- State
- Published
- Severity
- 9.2 Critical
- Published
- Aug 25, 2026
- Updated
- Aug 25, 2026
- Reserved
- Aug 24, 2026
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.
Scores
| CVSS | Score | Vector | Source |
|---|---|---|---|
| 4.0 | 9.2 Critical | CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N | AMZN |
| 3.1 | 8.1 High | CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H | AMZN |
Weaknesses
- CWE-1427 Improper Neutralization of Input Used for LLM Prompting
Affected Products
| Product | Versions |
|---|---|
strands-agents-toolsAmazon |
|
References
- https://pypi.org/project/strands-agents-tools/0.8.5/patchrelease-notes
- https://aws.amazon.com/security/security-bulletins/2026-089-aws/vendor-advisory
Every record here comes from the CVE Program’s CVE List. © 1999–2026 The MITRE Corporation. CVE is a registered trademark of The MITRE Corporation. The records are reproduced under the CVE Program terms of use.