CVE-2025-1040
HIGHAutoGPT < 0.4.0 - Server-Side Template Injection via AgentOutputBlock Format String
Title source: llmExploitation Summary
EIP tracks 1 public exploit for CVE-2025-1040. PoCs published by Acczdy.
AI-analyzed exploit summary The repository contains a Python script template for CVE-2025-1040 with placeholder functions and minimal implementation. The README lacks technical details and the exploit function is not implemented.
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.
Exploits (1)
The repository contains a Python script template for CVE-2025-1040 with placeholder functions and minimal implementation. The README lacks technical details and the exploit function is not implemented.
References (2)
Scores
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H