{"answers":{"affected":"","exploited":"It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-33234 exists.","fix":"No fix has been published for CVE-2026-33234 yet. Limit exposure of the affected software until one is available.","what":"CVE-2026-33234 is a medium-severity server-side request forgery vulnerability in Significant-Gravitas AutoGPT, published on 19 May 2026. Any signed-in user can exploit it over the network, with no action from the victim."},"fix_prompt":"Check this codebase for CVE-2026-33234 and fix it if it is affected.\n\nWhat it is: CVE-2026-33234 is a medium-severity server-side request forgery vulnerability in Significant-Gravitas AutoGPT, published on 19 May 2026. Any signed-in user can exploit it over the network, with no action from the victim.\nExploitation: It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-33234 exists.\n\nAffected product: Significant-Gravitas AutoGPT. No package-level version data is available, so check the vendor advisory linked from the reference page.\n\nTask:\n1. Search the dependency manifests and lockfiles (for example package.json, package-lock.json, requirements.txt, poetry.lock, uv.lock, pom.xml, build.gradle, go.mod, Cargo.lock, Gemfile.lock) and any Dockerfiles for the affected packages, including transitive dependencies.\n2. If an affected version is in use, upgrade it to the fixed version for its release line with the project's package manager, so the lockfile is regenerated. Prefer the smallest upgrade that fixes it.\n3. If there is no fix, or the upgrade would break the build, do not guess: explain the risk and the safest workaround instead.\n4. Run the tests and summarise what changed and why.\n5. If nothing in the project is affected, say so and change nothing.\n\nReference: https://insights.sbomify.com/CVE-2026-33234/ (Markdown: https://insights.sbomify.com/CVE-2026-33234/index.md)","id":"CVE-2026-33234","markdown":"https://insights.sbomify.com/CVE-2026-33234/index.md","name":"CVE-2026-33234","record":{"aliases":["GHSA-4jwj-6mg5-wrwf"],"analysis":{"component_type":"web_application","fix_type":"upgrade","impacts":["data_read","security_bypass"],"network_reachable":"yes","non_default_config":false,"product_category":"AutoGPT platform","requires_auth":"low_privilege","summary":"Authenticated users can bypass SSRF protections in AutoGPT's SendEmailBlock to scan internal networks and read service banners via user-controlled SMTP settings.","user_interaction":"not_required","vuln_class":"ssrf"},"analysis_generated_by":"qwen3.8-flash-next","assigner":"GitHub_M","cpe":[],"cvss":{"score":5,"severity":"medium","source":"cna","vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:L/I:N/A:N","version":"3.1"},"cwes":[{"id":"CWE-918","name":"Server-Side Request Forgery"}],"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.","ecosystems":[],"exploits":{"exploitdb":0,"first_seen":"2026-09-07","github_poc":1,"max_poc_stars":0,"metasploit":0,"nuclei":0,"refs":[{"date":"2026-09-07T11:27:08Z","kind":"github_poc","ref":"https://github.com/pavanchow/CVE-2026-33234","stars":0,"title":"SSRF via smtplib raw TCP sockets bypassing HTTP blocklist in AutoGPT SendEmailBlock"}],"tier":"weaponised"},"has_fix":false,"headline":"AutoGPT: SendEmailBlock's IP blocklist bypass allows SSRF via user-controlled SMTP server","id":"CVE-2026-33234","indexable":true,"kev":null,"kind":"cve","links":{"ecosystem":null,"product":null,"products":[],"type":"ssrf","year":"2026"},"n_packages":0,"n_references":2,"next":{"headline":"AutoGPT: Denial of Service (DoS) via Resource Exhaustion in text templating features","id":"CVE-2026-33235"},"packages":[],"prev":{"headline":"AutoGPT Platform: Remote Code Execution via Unsafe Pickle Deserialization of Redis Cache Entries","id":"CVE-2026-33233"},"products":["AutoGPT"],"published":"2026-05-19","related":[],"sources":[{"class":"attribution","licence":"CVE Terms of Use (MITRE)","name":"CVE List","prefix":"CVE"},{"class":"attribution","licence":"CWE Terms of Use","name":"CWE (MITRE)"},{"class":"attribution","licence":"FIRST CVSS licence","name":"CVSS (FIRST)"},{"class":"open","licence":"CC0","name":"PoC-in-GitHub"}],"ssvc":{"automatable":"no","exploitation":"poc","technical_impact":"partial"},"state":"PUBLISHED","updated":"2026-05-19","vendors":["Significant-Gravitas"]},"summary":"Authenticated users can bypass SSRF protections in AutoGPT's SendEmailBlock to scan internal networks and read service banners via user-controlled SMTP settings.","url":"https://insights.sbomify.com/CVE-2026-33234/"}