{"api_version":"1","generated_at":"2026-05-19T04:26:29+00:00","cve":"CVE-2026-33234","urls":{"html":"https://cve.report/CVE-2026-33234","api":"https://cve.report/api/cve/CVE-2026-33234.json","docs":"https://cve.report/api","cve_org":"https://www.cve.org/CVERecord?id=CVE-2026-33234","nvd":"https://nvd.nist.gov/vuln/detail/CVE-2026-33234"},"summary":{"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.","state":"PUBLISHED","assigner":"GitHub_M","published_at":"2026-05-19 02:16:16","updated_at":"2026-05-19 02:16:16"},"problem_types":["CWE-918","CWE-918 CWE-918: Server-Side Request Forgery (SSRF)"],"metrics":[{"version":"3.1","source":"security-advisories@github.com","type":"Secondary","score":"5","severity":"MEDIUM","vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:L/I:N/A:N","data":{"version":"3.1","vectorString":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:L/I:N/A:N","baseScore":5,"baseSeverity":"MEDIUM","attackVector":"NETWORK","attackComplexity":"LOW","privilegesRequired":"LOW","userInteraction":"NONE","scope":"CHANGED","confidentialityImpact":"LOW","integrityImpact":"NONE","availabilityImpact":"NONE"}},{"version":"3.1","source":"CNA","type":"DECLARED","score":"5","severity":"MEDIUM","vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:L/I:N/A:N","data":{"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"}}],"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","refsource":"security-advisories@github.com","tags":[],"title":"","mime":"","httpstatus":"","archivestatus":"0"},{"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","refsource":"security-advisories@github.com","tags":[],"title":"","mime":"","httpstatus":"","archivestatus":"0"},{"url":"https://www.cve.org/CVERecord?id=CVE-2026-33234","name":"CVE Program record","refsource":"CVE.ORG","tags":["canonical"]},{"url":"https://nvd.nist.gov/vuln/detail/CVE-2026-33234","name":"NVD vulnerability detail","refsource":"NVD","tags":["canonical","analysis"]}],"affected":[{"source":"CNA","vendor":"Significant-Gravitas","product":"AutoGPT","version":"affected >= 0.1.0, < 0.6.52","platforms":[]}],"timeline":[],"solutions":[],"workarounds":[],"exploits":[],"credits":[],"nvd_cpes":[],"vendor_comments":[],"enrichments":{"kev":null,"epss":null,"legacy_qids":[]},"source_records":{"cve_program":{"containers":{"cna":{"affected":[{"product":"AutoGPT","vendor":"Significant-Gravitas","versions":[{"status":"affected","version":">= 0.1.0, < 0.6.52"}]}],"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."}],"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","description":"CWE-918: Server-Side Request Forgery (SSRF)","lang":"en","type":"CWE"}]}],"providerMetadata":{"dateUpdated":"2026-05-19T00:51:41.350Z","orgId":"a0819718-46f1-4df5-94e2-005712e83aaa","shortName":"GitHub_M"},"references":[{"name":"https://github.com/Significant-Gravitas/AutoGPT/security/advisories/GHSA-4jwj-6mg5-wrwf","tags":["x_refsource_CONFIRM"],"url":"https://github.com/Significant-Gravitas/AutoGPT/security/advisories/GHSA-4jwj-6mg5-wrwf"},{"name":"https://github.com/Significant-Gravitas/AutoGPT/releases/tag/autogpt-platform-beta-v0.6.52","tags":["x_refsource_MISC"],"url":"https://github.com/Significant-Gravitas/AutoGPT/releases/tag/autogpt-platform-beta-v0.6.52"}],"source":{"advisory":"GHSA-4jwj-6mg5-wrwf","discovery":"UNKNOWN"},"title":"AutoGPT: SendEmailBlock's IP blocklist bypass allows SSRF via user-controlled SMTP server"}},"cveMetadata":{"assignerOrgId":"a0819718-46f1-4df5-94e2-005712e83aaa","assignerShortName":"GitHub_M","cveId":"CVE-2026-33234","datePublished":"2026-05-19T00:51:41.350Z","dateReserved":"2026-03-18T02:42:27.508Z","dateUpdated":"2026-05-19T00:51:41.350Z","state":"PUBLISHED"},"dataType":"CVE_RECORD","dataVersion":"5.2"},"nvd":{"publishedDate":"2026-05-19 02:16:16","lastModifiedDate":"2026-05-19 02:16:16","problem_types":["CWE-918","CWE-918 CWE-918: Server-Side Request Forgery (SSRF)"],"metrics":{"cvssMetricV31":[{"source":"security-advisories@github.com","type":"Secondary","cvssData":{"version":"3.1","vectorString":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:L/I:N/A:N","baseScore":5,"baseSeverity":"MEDIUM","attackVector":"NETWORK","attackComplexity":"LOW","privilegesRequired":"LOW","userInteraction":"NONE","scope":"CHANGED","confidentialityImpact":"LOW","integrityImpact":"NONE","availabilityImpact":"NONE"},"exploitabilityScore":3.1,"impactScore":1.4}]},"configurations":[]},"legacy_mitre":{"record":{"CveYear":"2026","CveId":"33234","Ordinal":"1","Title":"AutoGPT: SendEmailBlock's IP blocklist bypass allows SSRF via us","CVE":"CVE-2026-33234","Year":"2026"},"notes":[{"CveYear":"2026","CveId":"33234","Ordinal":"1","NoteData":"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.","Type":"Description","Title":"AutoGPT: SendEmailBlock's IP blocklist bypass allows SSRF via us"}]}}}