Amazon Strands Agents Tools 0.8.4 LLM Prompting RCE via python_repl
CVE-2026-78379 Published on August 25, 2026
Consent bypass in python_repl tool via batch kwargs forwarding in Amazon Strands Agents Tools
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.
Vulnerability Analysis
CVE-2026-78379 can be exploited with network access, and does not require authorization privileges or user interaction. This vulnerability is considered to have a low attack complexity. The potential impact of an exploit of this vulnerability is considered to have no impact on confidentiality and integrity and availability.
Weakness Type
Products Associated with CVE-2026-78379
Want to know whenever a new CVE is published for Amazon Strands Agents Tools? stack.watch will email you.
Affected Versions
Amazon strands-agents-tools:- Before 0.8.5 is affected.