Vulnerability in Amazon Strands-Agents-Tools

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 · last modified .

CVSS v3 metric

CVSS v3 base score 8.1 (High). Vector: CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H.

EPSS exploit prediction

EPSS: 0.006 (45.8th percentile), scored .

Very low probability of exploitation in the next 30 days; routine patching cadence is appropriate. 46th percentile — 45.8% of CVEs in the catalogue have a lower EPSS than this one. How to read EPSS.

EPSS trend (30 days)EPSS over the last 30 days for CVE-2026-78379: held from 0.003 to 0.006.

EPSS over last 30 days · oldest: 0.003 · newest: 0.006 · change: +0.003

Affected products

Weakness classification (CWE)

References

Frequently asked questions

What is CVE-2026-78379?
CVE-2026-78379 is a high-severity vulnerability in Amazon Strands-Agents-Tools, classified under CWE-1427. CVSS score: 8.1/10. Published 2026-08-25.
How severe is CVE-2026-78379?
High severity. CVSS v3 base score is 8.1 out of 10.