# CVE-2026-78379

## Summary

- **CVE ID:** CVE-2026-78379
- **Severity:** CRITICAL
- **CVSS Score:** 9.2 (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)
- **CWE:** CWE-1427
- **Published:** Aug 25, 2026
- **Last Modified:** Aug 25, 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.

## Affected Products

- Amazon — strands-agents-tools (0)

## References

- [CNA](https://pypi.org/project/strands-agents-tools/0.8.5/)
- [CNA](https://aws.amazon.com/security/security-bulletins/2026-089-aws/)

## Exploitation Prediction (EPSS)

- **EPSS Score:** 0.32%
- **EPSS Percentile:** 24.5

---
_Exported from OnDuty AI Vulnerability Intelligence on 2026-09-09._