{"id":"CVE-2026-33234","state":"PUBLISHED","title":"AutoGPT: SendEmailBlock's IP blocklist bypass allows SSRF via user-controlled SMTP server","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.","publishedAt":"2026-05-19T00:51:41.350Z","updatedAt":"2026-05-19T16:29:31.550Z","severity":{"score":5,"label":"Medium","version":"3.1","vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:L/I:N/A:N","source":"GitHub_M"},"assigner":"GitHub_M","products":["Significant-Gravitas AutoGPT"],"affected":[{"vendor":"Significant-Gravitas","product":"AutoGPT","versions":[{"version":">= 0.1.0, < 0.6.52","status":"affected"}]}],"references":["https://github.com/Significant-Gravitas/AutoGPT/security/advisories/GHSA-4jwj-6mg5-wrwf","https://github.com/Significant-Gravitas/AutoGPT/releases/tag/autogpt-platform-beta-v0.6.52"],"weaknesses":["CWE-918"],"ingestedAt":"2026-10-29T20:11:40.391Z","source":{"repository":"CVEProject/cvelistV5","path":"cves/2026/33xxx/CVE-2026-33234.json","commit":"556c9d3a8cd17e218bb8e452ba7cd619a384ff47"},"raw":{"dataType":"CVE_RECORD","dataVersion":"5.2","cveMetadata":{"cveId":"CVE-2026-33234","state":"PUBLISHED","datePublished":"2026-05-19T00:51:41.350Z","dateUpdated":"2026-05-19T16:29:31.550Z","assignerShortName":"GitHub_M","assignerOrgId":"a0819718-46f1-4df5-94e2-005712e83aaa","dateReserved":"2026-03-18T02:42:27.508Z"},"containers":{"cna":{"title":"AutoGPT: SendEmailBlock's IP blocklist bypass allows SSRF via user-controlled SMTP server","descriptions":[{"lang":"en","value":"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."}],"affected":[{"vendor":"Significant-Gravitas","product":"AutoGPT","versions":[{"version":">= 0.1.0, < 0.6.52","status":"affected"}]}],"references":[{"url":"https://github.com/Significant-Gravitas/AutoGPT/security/advisories/GHSA-4jwj-6mg5-wrwf","name":"https://github.com/Significant-Gravitas/AutoGPT/security/advisories/GHSA-4jwj-6mg5-wrwf","tags":["x_refsource_CONFIRM"]},{"url":"https://github.com/Significant-Gravitas/AutoGPT/releases/tag/autogpt-platform-beta-v0.6.52","name":"https://github.com/Significant-Gravitas/AutoGPT/releases/tag/autogpt-platform-beta-v0.6.52","tags":["x_refsource_MISC"]}],"metrics":[{"cvssV3_1":{"attackComplexity":"LOW","attackVector":"NETWORK","availabilityImpact":"NONE","baseScore":5,"baseSeverity":"MEDIUM","confidentialityImpact":"LOW","integrityImpact":"NONE","privilegesRequired":"LOW","scope":"CHANGED","userInteraction":"NONE","vectorString":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:L/I:N/A:N","version":"3.1"}}],"problemTypes":[{"descriptions":[{"cweId":"CWE-918","lang":"en","description":"CWE-918: Server-Side Request Forgery (SSRF)","type":"CWE"}]}],"providerMetadata":{"shortName":"GitHub_M","orgId":"a0819718-46f1-4df5-94e2-005712e83aaa","dateUpdated":"2026-05-19T00:51:41.350Z"},"source":{"advisory":"GHSA-4jwj-6mg5-wrwf","discovery":"UNKNOWN"}},"adp":[{"title":"CISA ADP Vulnrichment","references":[{"url":"https://github.com/Significant-Gravitas/AutoGPT/security/advisories/GHSA-4jwj-6mg5-wrwf","tags":["exploit"]}],"metrics":[{"other":{"type":"ssvc","content":{"timestamp":"2026-05-19T16:28:15.558069Z","id":"CVE-2026-33234","options":[{"Exploitation":"poc"},{"Automatable":"no"},{"Technical Impact":"partial"}],"role":"CISA Coordinator","version":"2.0.3"}}}],"providerMetadata":{"shortName":"CISA-ADP","orgId":"134c704f-9b21-4f2e-91b3-4a467353bcc0","dateUpdated":"2026-05-19T16:29:31.550Z"}}]}}}