CVE-2026-78379EPSS p45.5%

CVE-2026-78379CVE-2026-78379

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.

Scoring

CVSS 8.1 ()
VectorCVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H
EPSS0.57% probability of exploitation · percentile 45.5% · 2026-10-05T12:00:23Z
Last modified2026-08-26
Sourced from NVD + FIRST.org EPSS. Curated for EU compliance use cases by Adam Lundqvist, Founder at SQUR.