Detections
Analytics

CVE-2026-51857

critical

Description

In camel-ai camel 0.2.91a1, v0.2.91a2 and v0.2.91a3, CodeExecutionToolkit can run model-produced Python code through SubprocessInterpreter without an approval boundary.

References

https://github.com/camel-ai/camel/issues/4037

https://gist.github.com/Ro1ME/78606e0763520d6519897e90b305d3cd

https://euvd.enisa.europa.eu/vulnerability/EUVD-2026-90423

Details

Source: Mitre, NVD

Published: 2026-09-30

Updated: 2026-10-01

Risk Information

CVSS v2

Base Score: 7.5

Vector: CVSS2#AV:N/AC:L/Au:N/C:P/I:P/A:P

Severity: High

CVSS v3

Base Score: 9.8

Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

Severity: Critical