VulnSocial

CVE-2026-33234Disclosure

MEDIUMCVSS 5.0 · MEDIUM

Exploit discussion active in current signal (1 latest mentions)

Immediate actions

  • Patch affected systems immediately
  • Hunt for exploitation attempts and persistence artifacts
  • Increase monitoring for publicly documented tradecraft

Recommended action window: High priority (within 72h)

NVD description

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.

Back to dashboard
4.0/ 10 priority

Sources & remediation

Other references
Weakness type (CWE)
CWE-918

Priority

MEDIUM

Exploitation

NONE

PoC

YES

Patch

AVAILABLE

Momentum

STABLE

Threat summary

  • Public PoC and exploit tooling are both present
  • Patch or workaround signal is available
  • 4 mentions across 2 observed days
  • Momentum state: stable

What's happening

  • Exploit tool or code specified in 1 signal
  • PoC mentioned or linked in 1 signal
  • Patch or workaround mentioned in 1 signal
  • Technical details provided in 3 signals
  • Disclosure: 1 classified signal
  • General: 1 classified signal
  • Peaked 1d ago at 3 mentions (2026-05-19); latest day: 1
  • 4 total mentions across 2 days

Deep dive

Activity timeline4 mentions / 2d
01223Mentions · 2026-05-19: 3Mentions · 2026-09-07: 1PoC Mentioned / Linked · 2026-09-07: 1Exploit Tool / Code · 2026-09-07: 1Patch / Workaround · 2026-05-19: 1Technical Details · 2026-05-19: 2Technical Details · 2026-09-07: 105-1909-07
Signal classification4 categories
Disclosure
125.0%
General
125.0%
Patch
125.0%
PoC
125.0%
Referenced assets3 URLs
Classification over time
DateTotalLabels
2026-05-193
Disclosure1General1Patch1
2026-09-071
PoC1
Full discourse4 posts
  • Clandestine@akaclandestine
    PoC

    GitHub - pavanchow/CVE-2026-33234: SSRF via smtplib raw TCP sockets bypassing HTTP blocklist in AutoGPT SendEmailBlock · GitHub https://github.com/pavanchow/CVE-2026-33234

    Post summary

    The GitHub repository provides proof‑of‑concept code demonstrating an SSRF flaw (CVE‑2026‑33234) in AutoGPT’s SendEmailBlock by using smtplib raw TCP sockets to bypass HTTP blocklists. No evidence of widespread exploitation or patch status is mentioned.

    0101153.1K
    64.8K followersView on X
  • NerdieNews@NewsNerdie
    Patch

    ⚠️ CVE-2026-33234: AutoGPT's SendEmailBlock can be exploited to bypass IP blocklists, enabling SSRF via user-controlled SMTP servers. This agentic AI flaw poses serious risks—patch now. #NerdieNews #CyberSecurity #Ransomware https://t.co/y8apL9FLSw

    Post summary

    The tweet announces CVE-2026-33234 in AutoGPT's SendEmailBlock, highlights its SSRF exploitation vector, and urges users to apply the patch immediately.

    00021109
    67 followersView on X
  • CVE@CVEnew
    General

    CVE-2026-33234 AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents. In versions 0.1.0 through 0.6.51, SendEmai… https://www.cve.org/CVERecord?id=CVE-2026-33234

    Post summary

    The message references CVE‑2026‑33234 for AutoGPT with minimal version details and no actionable information such as a PoC, exploit, or patch.

    00000165
    57.5K followersView on X
  • Vulmon Vulnerability Feed@VulmonFeeds
    Disclosure

    CVE-2026-33234 Server-Side Request Forgery in AutoGPT SendEmailBlock Versions 0.1.0 Through 0.6.51 https://vulmon.com/vulnerabilitydetails?qid=CVE-2026-33234

    Post summary

    The entry announces a newly disclosed Server‑Side Request Forgery (SSRF) vulnerability (CVE‑2026‑33234) affecting AutoGPT SendEmailBlock versions 0.1.0 through 0.6.51, with a reference to a vulnerability database page.

    0000064
    4.0K followersView on X

Explore more

Back to dashboard