{"schemaVersion":1,"url":"https://cve.openhack.com/cve/CVE-2026-33234","id":"CVE-2026-33234","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 TC","descriptionLong":"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.","published":"2026-05-19T00:51:41.350Z","updated":"2026-10-28T02:30:32.142134134Z","reserved":"2026-03-18T02:42:27.508Z","status":"Deferred","rejected":false,"assigner":"GitHub_M","metric":{"version":"3.1","score":5,"vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:L/I:N/A:N","rating":"medium","source":"GitHub_M"},"metrics":[{"version":"3.1","score":5,"vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:L/I:N/A:N","rating":"medium","source":"GitHub_M"},{"version":"3.1","score":5,"vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:L/I:N/A:N","rating":"medium","source":"github.com"},{"version":"3.1","score":5,"vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:L/I:N/A:N","rating":"medium","source":"OSV"}],"rating":"medium","products":["Significant-Gravitas AutoGPT"],"affectedProducts":[{"vendor":"Significant-Gravitas","product":"AutoGPT","defaultStatus":null,"versions":[{"version":">= 0.1.0, < 0.6.52","status":"affected"}],"platforms":[]}],"packages":[],"cwes":["CWE-918"],"aliases":["GHSA-4jwj-6mg5-wrwf"],"references":[{"url":"https://github.com/Significant-Gravitas/AutoGPT/security/advisories/GHSA-4jwj-6mg5-wrwf","tags":["x_refsource_CONFIRM","exploit","advisory"]},{"url":"https://github.com/Significant-Gravitas/AutoGPT/releases/tag/autogpt-platform-beta-v0.6.52","tags":["x_refsource_MISC","web"]},{"url":"https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/33xxx/CVE-2026-33234.json","tags":["advisory"]},{"url":"https://nvd.nist.gov/vuln/detail/CVE-2026-33234","tags":["advisory"]}],"patchReferenced":false,"fixAvailable":false,"exploitReferenced":true,"kev":false,"kevAdded":null,"kevDue":null,"kevEntry":null,"ssvc":{"exploitation":"poc","automatable":"no","technicalImpact":"partial"},"epss":0.00304,"epssPercentile":0.23499,"sources":[{"name":"CVE List","url":"https://www.cve.org/CVERecord?id=CVE-2026-33234","ok":true},{"name":"NVD","url":"https://nvd.nist.gov/vuln/detail/CVE-2026-33234","ok":true,"note":"Deferred"},{"name":"OSV","url":"https://osv.dev/vulnerability/CVE-2026-33234","ok":true,"note":"0 packages"},{"name":"CISA KEV","url":"https://www.cisa.gov/known-exploited-vulnerabilities-catalog","ok":true,"note":"not listed"},{"name":"EPSS","url":"https://api.first.org/data/v1/epss?cve=CVE-2026-33234","ok":true,"note":"scored 2026-11-18"}],"aiTitle":false,"tech":[],"critical":[],"attention":null}