What’s Vulnerable › Vulnerabilities

CVE-2026-78379: Consent bypass in python_repl tool via batch kwargs forwarding in Amazon Strands Agents Tools

• Severity: high (CVSS 8.1 v3.1)
• Exploited in the wild: not listed in CISA KEV
• EPSS: 0.6% probability of exploitation in the next 30 days
• Public exploit or detection template: none known
• Published: 2026-08-25 · updated 2026-08-26
• Weakness: CWE-1427

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

• AWS strands-agents-tools: before 0.8.5 — fixed in 0.8.5

How to fix

Upgrade to a fixed version: AWS strands-agents-tools 0.8.5. Check the vendor advisory for mitigations.

References

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

Get alerted when CVE-2026-78379 or the next vulnerability affects your stack