---
cve: "CVE-2026-78379"
severity: "CRITICAL"
cvss: 9.2
epss: "0.3%"
vendor: "Amazon"
kev: false
exploited: false
published: "2026-08-25 19:16:54"
tags: [cve, security, critical]
source: tsecurity.de CVE-Dossier
exported: "2026-09-25T20:36:06+02:00"
---

# CVE-2026-78379

> 9.2 CRITICAL

## Beschreibung

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.

## CVSS-Vektor

```
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
```

| Metrik | Wert | Bewertung |
|---|---|---|
| AV Angriffsvektor | Netzwerk | bad |
| AC Komplexität | Gering | bad |
| PR Privilegien | Keine | bad |
| UI Interaktion | Keine | bad |

## Referenzen

- <https://pypi.org/project/strands-agents-tools/0.8.5/>
- <https://aws.amazon.com/security/security-bulletins/2026-089-aws/>

---
_Exportiert aus dem [tsecurity.de CVE-Dossier](https://tsecurity.de/cve?cve=CVE-2026-78379) · Datenquellen: EUVD (ENISA), NVD, OSV, CISA KEV, FIRST EPSS, Exploit-DB, BSI BITS_