Cyber Posture

CVE-2025-1040

HighPublic PoC

Published: 20 March 2025

Published
20 March 2025
Modified
15 October 2025
KEV Added
Patch
CVSS Score 8.8 CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
EPSS Score 0.1160 93.7th percentile
Risk Priority 25 60% EPSS · 20% KEV · 20% CVSS

Description

Adversaries may abuse command and script interpreters to execute commands, scripts, or binaries.

Security Summary

CVE-2025-1040 is a Server-Side Template Injection (SSTI) vulnerability affecting AutoGPT versions 0.3.4 and earlier. The flaw stems from improper handling of user-supplied format strings in the AgentOutputBlock implementation, where malicious input is passed directly to the Jinja2 templating engine without sufficient security controls, enabling Remote Code Execution (RCE). It is classified under CWE-1336 with a CVSS v3.1 base score of 8.8 (AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H).

An attacker with low privileges, such as an authenticated user, can exploit this vulnerability remotely over the network with low attack complexity and no user interaction required. Exploitation involves injecting malicious templates that execute arbitrary commands on the host system, granting high-impact access to confidentiality, integrity, and availability.

The issue is addressed in AutoGPT version 0.4.0. The fixing commit is documented at https://github.com/significant-gravitas/autogpt/commit/6dba31e0215549604bdcc1aed24e3a1714e75ee2, with additional details available via the Huntr bounty report at https://huntr.com/bounties/b74ef75f-61d5-4422-ab15-9550c8b4f185.

Details

CWE(s)
CWE-1336

Affected Products

agpt
autogpt platform
≤ 0.4.0

MITRE ATT&CK Enterprise Techniques

T1190 Exploit Public-Facing Application Initial Access
Adversaries may attempt to exploit a weakness in an Internet-facing host or system to initially access a network.
T1059 Command and Scripting Interpreter Execution
Adversaries may abuse command and script interpreters to execute commands, scripts, or binaries.
Why these techniques?

SSTI vulnerability directly enables remote exploitation of the application for arbitrary command execution (RCE) on the host.

Confidence: HIGH · MITRE ATT&CK Enterprise v19.0

References