CVE-2025-1040Public exploitNetwork attack vector

Authenticated command execution via unsandboxed Jinja templates

Published Mar 20, 2025 · Updated Oct 15, 2025

Server-side template injection in AutoGPT 0.3.4 and earlier allows remote authenticated users to execute arbitrary host commands. AgentOutputBlock passes a user-controlled format string to an unrestricted Jinja2 environment, which compiles and renders the string as a template. A valid account and control of the block's format input are required, and successful exploitation runs commands with the backend process's privileges.

CVSS severity8.8
High
EPSS probability1.72%
Next 30 days · Sep 16, 2026
Known exploitationUnconfirmed
Based on sourced intelligence
Hinoki checkNot available
Coverage for this vulnerability

See if you're affected

Explore vulnerability checks for your environment with Hinoki.

Book a demo

Summary

What happened

Server-side template injection in AutoGPT 0.3.4 and earlier allows remote authenticated users to execute arbitrary host commands. AgentOutputBlock passes a user-controlled format string to an unrestricted Jinja2 environment, which compiles and renders the string as a template. A valid account and control of the block's format input are required, and successful exploitation runs commands with the backend process's privileges.

The record

CVE
CVE-2025-1040
Published
Mar 20, 2025
Updated
Oct 15, 2025
Vendor
Significant Gravitas
Product
AutoGPT
Classifications
CWE-1336, T1059
Attack vector
network
Privileges
authenticated

Timeline

How it unfolded

  1. Mar 20, 2025CVE publishedPublication date reported by the CVE source.
  2. Oct 15, 2025Record updatedLatest update available in the CVE record.

Exploitability

Present is not the same as exploitable

Compare your product and version with the public record. A matching version still requires validation against your environment.

Is a vulnerable build present?

Compare these published version ranges with your installed build and any vendor patches.

  1. Affected versionversion=unspecified <v0.4.0

What conditions does exploitation require?

Attack vectornetwork
Required privilegesauthenticated

What is affected?

Significant Gravitas · AutoGPTversion=unspecified <v0.4.0

Published CVSS scores

8.8NIST NVDCVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

CVSS describes severity. EPSS estimates exploitation probability.

Attacks

What attackers are doing with it

Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.

Daily unique IPsNo honeypot observations are available for this CVE in the selected window.

No observations available

Sep 10, 2026Sep 16, 2026
Latest reporting daySep 16, 2026
Latest daily unique IPsUnavailable
Prior 30-day averageUnavailable
SourceShadowserver honeypots (KEV)
Vectornetwork
Privilegesauthenticated
Known exploitationUnconfirmed
Public exploitPublished

Weakness, pattern, technique

CWE-1336Improper Neutralization of Special Elements Used in a Template Engine
T1059Command and Scripting Interpreter

Public exploit references

Labels summarize the accepted research assessment. They do not indicate a test against your environment.

Technologies

Your stack

See the directory against your own environment.

Your stack

Check the software in your environment

Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.

Book a demo