CVE Feed

    Dashboard / CVE / CVE-2026-78379

    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
    Amazon
    Product
    Strands-agents-tools

    Exploits

    No exploit reference

    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