NVD Vulnerability Detail
Search Exploit, PoC
CVE-2026-33234
Summary

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.

Publication Date May 19, 2026, 11:16 a.m.
Registration Date May 20, 2026, 4:11 a.m.
Last Update May 20, 2026, 2:16 a.m.
CVSS3.1 : MEDIUM
スコア 5.0
Vector CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:L/I:N/A:N
攻撃元区分(AV) ネットワーク
攻撃条件の複雑さ(AC)
攻撃に必要な特権レベル(PR)
利用者の関与(UI) 不要
影響の想定範囲(S) 変更あり
機密性への影響(C)
完全性への影響(I) なし
可用性への影響(A) なし
Related information, measures and tools
Common Vulnerabilities List