AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents
AutoGPT versions 0.1.0-0.6.51 have a Server-Side Request Forgery (SSRF) bypass in the `SendEmailBlock`, allowing authenticated users to specify arbitrary SMTP server and port details. This circumvents existing IP validation, enabling internal network port scanning and service fingerprinting, as error messages expose target TCP banners.
AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents. In versions 0.1.0 through 0.6.51, SendEmailBlock in autogpt_platform/backend/backend/blocks/email_block.py accepts a user-supplied smtp_server (string) and smtp_port (integer) as per-execution block inputs, then passes them directly to Python's smtplib.SMTP() to open a raw TCP connection with no IP address validation. This completely bypasses the platform's hardened SSRF protections in backend/util/request.py — the validate_url_host() function and BLOCKED_IP_NETWORKS blocklist that every other block uses to block connections to private, loopback, link-local, and cloud metadata addresses. An authenticated user on a shared AutoGPT deployment can use this to perform non-blind internal network port scanning and service fingerprinting: smtplib reads the target's TCP banner on connect and embeds it in the exception message, which is persisted as user-visible block output via the execution framework. This issue has been fixed in version 0.6.52.
Authenticated users on shared AutoGPT deployments are at medium risk of performing internal network reconnaissance, which can aid in mapping and exploiting private network services.
Monitor & Review
Low severity — keep this CVE on your radar and patch during routine maintenance.
What should I do?
Published
CVE disclosed publicly
Last Modified
Most recent update
Indexed to CVEInsight
Added to this platform
AV:N/AC:L/PR:L/UI:N/S:C/C:L/I:N/A:N
0
Affected Products
2
References
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:L/I:N/A:N
Exploitability
Impact