AutoGPT: SendEmailBlock's IP blocklist bypass allows SSRF via user-controlled SMTP server
Key facts
- Attack vector
- Network
- Privileges required
- Low
- User interaction
- None
- Attack complexity
- Low
- Impact type
- Information disclosure
- Confidentiality · integrity · availability
- Low · None · None
- Fix status
- Fixed
Attack profile from CVSS 3.1 · CNA. Fix status from CNA. Impact type from CWE-918 and the CVSS impact.
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.
Why it matters now
SSVC decision points
CISA ADP · SSVC 2.0.3
- Exploitation
- Poc
- Automatable
- No
- Technical impact
- Partial
The decision (Track, Attend, Act) also depends on your mission and well-being impact; see CISA's SSVC guide.
Affected products
| Vendor | Product | Affected versions | Fixed in | Status | Source |
|---|---|---|---|---|---|
| Significant-Gravitas | AutoGPT | 0.1.0 to before 0.6.52 | 0.6.52 | Patch available | CNA |
- AutoGPT VendorSignificant-Gravitas Affected 0.1.0 to before 0.6.52 Fixed in 0.6.52 Patch available CNA
CPE names Threatist (inferred) · 1
Inferred from how NVD named this product before; not given by a source.
| CPE | Versions | Role | Vendor |
|---|---|---|---|
| cpe:2.3:a:agpt:autogpt_platform:*:*:*:*:*:*:*:* | — | — | Significant-Gravitas |
- cpe:2.3:a:agpt:autogpt_platform:*:*:*:*:*:*:*:* Versions — — ·Significant-Gravitas
Remediation
- Fix · CNA AutoGPT (Significant-Gravitas) Fixed in 0.6.52
Timeline
- 2026-10-02 Threatist record created from CVE-2026-33234
References
More Significant-Gravitas vulnerabilities
- TI-2024-05646 Shell Command Denylist Bypass in significant-gravitas/autogpt CVSS 3.1CRITICAL 9.8
- TI-2026-19981 AutoGPT is Vulnerable to RCE via Disabled Block Execution CVSS 4.0HIGH 8.6
- TI-2025-23508 AutoGPT has a DoS vulnerability in MediaDurationBlock CVSS 4.0HIGH 8.7
- TI-2025-23495 AutoGPT has a DoS vulnerability in ScreenshotWebPageBlock CVSS 4.0HIGH 8.7
- TI-2025-23493 AutoGPT has a DoS vulnerability in FileStoreBlock with StepThroughItemsBlock CVSS 4.0HIGH 8.7
- TI-2025-23471 AutoGPT has a DoS vulnerability in ReadRSSFeedBlock CVSS 4.0HIGH 8.7
Sources
This product uses the NVD API but is not endorsed or certified by the NVD. Sources and licences