Skip to main content
Press slash or control plus K to focus the search. Use the arrow keys to navigate results and press enter to open a threat.
Reconnecting to live updates…

CVE-2026-33234: CWE-918: Server-Side Request Forgery (SSRF) in Significant-Gravitas AutoGPT

0
Medium
VulnerabilityCVE-2026-33234cvecve-2026-33234cwe-918
Published: Tue May 19 2026 (05/19/2026, 00:51:41 UTC)
Source: CVE Database V5
Vendor/Project: Significant-Gravitas
Product: AutoGPT

Description

CVE-2026-33234 is a Server-Side Request Forgery (SSRF) vulnerability in Significant-Gravitas AutoGPT versions 0. 1. 0 through 0. 6. 51. The vulnerability arises because the SendEmailBlock accepts user-supplied SMTP server and port inputs and passes them directly to Python's smtplib. SMTP() without IP address validation. This bypasses the platform's usual SSRF protections, allowing an authenticated user on a shared deployment to perform internal network port scanning and service fingerprinting. The issue has been fixed in version 0. 6.

AI-Powered Analysis

Machine-generated threat intelligence

AILast updated: 05/19/2026, 01:36:55 UTC

Technical Analysis

AutoGPT is a workflow automation platform for AI agents. In versions 0.1.0 to 0.6.51, the SendEmailBlock component allows authenticated users to specify smtp_server and smtp_port parameters that are passed directly to smtplib.SMTP() without validation. This bypasses the platform's SSRF protections that normally block connections to private, loopback, link-local, and cloud metadata IP ranges. As a result, attackers can perform internal network reconnaissance by reading TCP banners from targeted hosts, which are exposed in error messages visible to the user. The vulnerability is tracked as CWE-918 and has a CVSS 3.1 base score of 5.0 (medium severity). It was fixed in version 0.6.52.

Potential Impact

An authenticated user on a shared AutoGPT deployment can exploit this vulnerability to conduct internal network port scanning and service fingerprinting. This could reveal information about internal services and network topology. The vulnerability does not directly allow data modification or denial of service but leaks internal network details via SMTP connection error messages.

Mitigation Recommendations

This vulnerability is fixed in AutoGPT version 0.6.52. Users should upgrade to version 0.6.52 or later to remediate this issue. Since the product is not a cloud service, remediation requires applying the official fix by upgrading. Patch status is not explicitly confirmed in the vendor advisory, but the fix is stated to be included in version 0.6.52. Until upgraded, restrict authenticated user permissions and avoid running shared deployments where untrusted users can specify SMTP parameters.

Pro Console: star threats, build custom feeds, automate alerts via Slack, email & webhooks.Upgrade to Pro

Technical Details

Data Version
5.2
Assigner Short Name
GitHub_M
Date Reserved
2026-03-18T02:42:27.508Z
Cvss Version
3.1
State
PUBLISHED
Remediation Level
null

Threat ID: 6a0bbb23ec166c07b029a366

Added to database: 5/19/2026, 1:21:39 AM

Last enriched: 5/19/2026, 1:36:55 AM

Last updated: 5/19/2026, 3:52:04 AM

Views: 7

Community Reviews

0 reviews

Crowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.

Sort by
Loading community insights…

Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.

Actions

PRO

Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.

Please log in to the Console to use AI analysis features.

Need more coverage?

Upgrade to Pro Console for AI refresh and higher limits.

For incident response and remediation, OffSeq services can help resolve threats faster.

Latest Threats

Breach by OffSeqOFFSEQFRIENDS — 25% OFF

Check if your credentials are on the dark web

Instant breach scanning across billions of leaked records. Free tier available.

Scan now
OffSeq TrainingCredly Certified

Lead Pen Test Professional

Technical5-day eLearningPECB Accredited
View courses