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.
Published:Aug 25, 2026
Last Modified:Aug 25, 2026
EPS:Aug 25, 2026
EPSS Score:
CVSS Score:8.1
Affected Products
Vendor
Product
Action
Vendor
Amazon
Product
Strands-agents-tools
Amazon
Strands-agents-tools
Exploits
No exploit reference
Common Weakness Enumeration
Common Attack Pattern Enumeration and Classification (CAPEC)
No CAPEC recorded yet
Common Vulnerability Scoring System
Attack Vector
Network
Adjacent
Local
Physical
Privileges Required
None
Low
High
User Interaction
None
Required
Scope
Unchanged
Changed
Confidentiality
None
Low
High
Integrity
None
Low
High
Availability
None
Low
High
