Consent bypass in python_repl tool via batch kwargs forwarding in Amazon Strands Agents Tools
Amazon strands-agents-tools
Affected versions
| Product | Affected | Fixed in |
|---|---|---|
| Amazon strands-agents-tools |
| No fix yet |
Original 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.
From the CVE record · AMZN