CVE-2026-51857 Details
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.
A vulnerability in Camel-AI versions 0.2.91a1, 0.2.91a2, and 0.2.91a3 allows the CodeExecutionToolkit to execute model-generated Python code via the SubprocessInterpreter. This occurs without any approval or oversight, creating a risk of unauthorized code execution in the local environment.
Users can update to Camel-AI version 0.2.91a5, which includes a confirmation requirement for executing code in the local subprocess.
Metrics
CVSS 4.0 Severity and Vector Strings:
CVSS 3.x Severity and Vector Strings:
No data available for CVSS Version 2.0 on this CVE.
Volerion
Assessed Sep 30, 2026CISA-ADP
Assessed Oct 2, 2026References to Advisories, Solutions, and Tools
By selecting these links, you will be leaving this site. These are references gathered from the official CVE record and are not endorsed by Volerion.
| URL | Source(s) | Tag(s) |
|---|---|---|
| https://github.com/camel-ai/camel/issues/4037 | CISA-ADP | ExploitIssue TrackingTechnical DescriptionVendor |
| https://gist.github.com/Ro1ME/78606e0763520d6519897e90b305d3cd | [email protected] | Technical Description |
| https://github.com/camel-ai/camel/issues/4037 | [email protected] | ExploitIssue TrackingTechnical DescriptionVendor |
Weakness Enumeration
| CWE-ID | CWE Name | Source |
|---|---|---|
| CWE-94 | Improper Control of Generation of Code ('Code Injection') | CISA-ADP |
Affected Products
| Product | Versions |
|---|---|
| camel-ai camel | >= 0.2.91a1, <= 0.2.91a3 |
CPE
Remediation
| |
Change History
2 change records found show changes
| Date | Action | Recorded By |
|---|---|---|
| Oct 2, 2026 | CVE Modified | CISA-ADP |
| Sep 30, 2026 | New CVE Received | [email protected] |
Volerion