AutoGPT versions 0.3.4 and earlier are vulnerable to a Server-Side Template Injection (SSTI) that could lead to Remote Code Execution (RCE). The vulnerability arises from the improper handling of user-supplied format strings in the `AgentOutputBlock` implementation, where malicious input is passed to the Jinja2 templating engine without adequate security measures. Attackers can exploit this flaw to execute arbitrary commands on the host system. The issue is fixed in version 0.4.0.
Advisories
Source ID Title
EUVD EUVD EUVD-2025-6829 AutoGPT versions 0.3.4 and earlier are vulnerable to a Server-Side Template Injection (SSTI) that could lead to Remote Code Execution (RCE). The vulnerability arises from the improper handling of user-supplied format strings in the `AgentOutputBlock` implementation, where malicious input is passed to the Jinja2 templating engine without adequate security measures. Attackers can exploit this flaw to execute arbitrary commands on the host system. The issue is fixed in version 0.4.0.
Fixes

Solution

No solution given by the vendor.


Workaround

No workaround given by the vendor.

History

Wed, 15 Oct 2025 22:30:00 +0900

Type Values Removed Values Added
Weaknesses CWE-77

Wed, 15 Oct 2025 22:00:00 +0900

Type Values Removed Values Added
Weaknesses CWE-1336

Wed, 06 Aug 2025 02:15:00 +0900

Type Values Removed Values Added
First Time appeared Agpt autogpt Platform
CPEs cpe:2.3:a:agpt:autogpt:*:*:*:*:*:*:*:* cpe:2.3:a:agpt:autogpt_platform:*:*:*:*:*:*:*:*
Vendors & Products Agpt autogpt
Agpt autogpt Platform

Wed, 02 Apr 2025 05:45:00 +0900

Type Values Removed Values Added
First Time appeared Agpt
Agpt autogpt
CPEs cpe:2.3:a:agpt:autogpt:*:*:*:*:*:*:*:*
Vendors & Products Agpt
Agpt autogpt
Metrics cvssV3_1

{'score': 8.8, 'vector': 'CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H'}


Fri, 21 Mar 2025 01:15:00 +0900

Type Values Removed Values Added
Metrics ssvc

{'options': {'Automatable': 'no', 'Exploitation': 'poc', 'Technical Impact': 'total'}, 'version': '2.0.3'}


Thu, 20 Mar 2025 19:15:00 +0900

Type Values Removed Values Added
Description AutoGPT versions 0.3.4 and earlier are vulnerable to a Server-Side Template Injection (SSTI) that could lead to Remote Code Execution (RCE). The vulnerability arises from the improper handling of user-supplied format strings in the `AgentOutputBlock` implementation, where malicious input is passed to the Jinja2 templating engine without adequate security measures. Attackers can exploit this flaw to execute arbitrary commands on the host system. The issue is fixed in version 0.4.0.
Title Server-Side Template Injection (SSTI) in significant-gravitas/autogpt
Weaknesses CWE-77
References
Metrics cvssV3_0

{'score': 8.8, 'vector': 'CVSS:3.0/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H'}


Projects

Sign in to view the affected projects.

cve-icon MITRE

Status: PUBLISHED

Assigner: @huntr_ai

Published:

Updated: 2025-10-15T12:50:50.369Z

Reserved: 2025-02-04T19:56:24.203Z

Link: CVE-2025-1040

cve-icon Vulnrichment

Updated: 2025-03-20T15:22:06.904Z

cve-icon NVD

Status : Modified

Published: 2025-03-20T10:15:53.653

Modified: 2025-10-15T13:16:01.167

Link: CVE-2025-1040

cve-icon Redhat

No data.

cve-icon OpenCVE Enrichment

No data.

Weaknesses