CVE-2026-33234
Server-Side Request Forgery in AutoGPT Platform
Publication date: 2026-05-19
Last updated on: 2026-05-19
Assigner: GitHub, Inc.
Description
Description
CVSS Scores
EPSS Scores
| Probability: | |
| Percentile: |
Meta Information
Affected Vendors & Products
| Vendor | Product | Version / Range |
|---|---|---|
| significant_gravitas | autogpt | From 0.1.0 (inc) to 0.6.52 (exc) |
| significant_gravitas | autogpt | 0.6.52 |
Helpful Resources
Exploitability
| CWE ID | Description |
|---|---|
| CWE-918 | The web server receives a URL or similar request from an upstream component and retrieves the contents of this URL, but it does not sufficiently ensure that the request is being sent to the expected destination. |
Attack-Flow Graph
AI Powered Q&A
Can you explain this vulnerability to me?
CVE-2026-33234 is a Server-Side Request Forgery (SSRF) vulnerability in the AutoGPT platform's SendEmailBlock. This block accepts user-supplied SMTP server and port inputs and passes them directly to Python's smtplib.SMTP() without validating the IP address.
Because of this lack of validation, the vulnerability bypasses the platform's hardened SSRF protections that normally block connections to private, loopback, link-local, and cloud metadata addresses.
An authenticated user on a shared AutoGPT deployment can exploit this to perform internal network port scanning and service fingerprinting by reading TCP banners from target services, which are then shown as error messages.
How can this vulnerability impact me? :
This vulnerability allows an authenticated user to scan internal network ports and fingerprint internal services such as SSH, Redis, and MySQL by extracting version information from TCP banners.
It can also confirm the reachability of cloud metadata endpoints, which may lead to further exploitation.
By identifying internal services and their versions, an attacker can enable lateral movement within the network by finding exploitable vulnerabilities in those services.
How can this vulnerability be detected on my network or system? Can you suggest some commands?
This vulnerability can be detected by monitoring for unusual SMTP connection attempts initiated by the AutoGPT SendEmailBlock with user-supplied smtp_server and smtp_port inputs. Since the vulnerability allows internal network port scanning and service fingerprinting via smtplib.SMTP(), detection can focus on identifying connections to internal IP ranges (such as 10.0.0.0/8, 172.16.0.0/12, 192.168.0.0/16, and cloud metadata IPs like 169.254.169.254) that are not typical for your environment.
You can use network monitoring tools or commands to detect these connections. For example, on a Linux system, you might use:
- tcpdump -i <interface> host <internal_IP_range> and port <smtp_port>
- netstat -anp | grep <smtp_port> to check for active SMTP connections initiated by AutoGPT processes.
- ss -tnp | grep <smtp_port> to list TCP connections and the processes using them.
Additionally, reviewing AutoGPT execution logs for error messages containing TCP banners from unexpected internal services can help identify exploitation attempts, as smtplib embeds these banners in exception messages visible to users.
What immediate steps should I take to mitigate this vulnerability?
The immediate mitigation step is to upgrade AutoGPT to version 0.6.52 or later, where this vulnerability has been fixed.
If upgrading is not immediately possible, you should restrict or validate the smtp_server and smtp_port inputs to ensure they do not allow connections to internal IP addresses or cloud metadata endpoints.
Additional mitigation includes implementing network-level controls such as firewall rules to block AutoGPT instances from making SMTP connections to internal or sensitive IP ranges.
Finally, monitor logs for suspicious SMTP connection attempts and error messages that may reveal internal service banners, and consider disabling or restricting the SendEmailBlock functionality for untrusted users.
How does this vulnerability affect compliance with common standards and regulations (like GDPR, HIPAA)?:
The vulnerability allows authenticated users to perform internal network port scanning and service fingerprinting by bypassing SSRF protections, potentially exposing internal network information.
Such exposure of internal network details and potential lateral movement could lead to unauthorized access to sensitive data, which may impact compliance with standards like GDPR and HIPAA that require protection of personal and sensitive information.
However, the provided context does not explicitly discuss the direct impact of this vulnerability on compliance with these regulations.