Güvenlik Zafiyet Raporu

CVE-2026-78379

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.

CVSS8.1
RiskHIGH
Yayın25.08.2026
KaynakNVD

Açıklama ve Etki

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.

Referanslar

Güvenli Doğrulama Notu

Bu sayfa saldırı gerçekleştiren payload'lar çalıştırmaz. Doğrulama; etkilenen ürün/sürümün envanterden kontrol edilmesi, üretici güvenlik duyurusunun incelenmesi ve güncellemenin uygulanması üzerinden yapılmalıdır.