{
  "threat_severity" : "Moderate",
  "public_date" : "2026-07-29T20:16:45Z",
  "bugzilla" : {
    "description" : "pydantic-ai: pydantic-ai-slim: Pydantic AI: Server-Side Request Forgery (SSRF) bypass exposes cloud credentials.",
    "id" : "2508674",
    "url" : "https://bugzilla.redhat.com/show_bug.cgi?id=2508674"
  },
  "cvss3" : {
    "cvss3_base_score" : "6.8",
    "cvss3_scoring_vector" : "CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:C/C:H/I:N/A:N",
    "status" : "draft"
  },
  "cwe" : "CWE-918",
  "details" : [ "Pydantic AI is a Python agent framework for building Generative AI applications. In versions 1.56.0 through 1.98.0, when an application opts a URL into force_download='allow-local' (disabling the default block on private/internal IPs), the cloud-metadata blocklist could be bypassed by encoding the metadata IP in an IPv6 transition form (IPv4-mapped IPv6, 6to4, or NAT64), exposing cloud IAM short-term credentials on dual-stack or translated networks. This is an incomplete fix of GHSA-2jrp-274c-jhv3 / CVE-2026-25580, whose remediation did not hold for IPv6-encoded forms of the metadata IPs. An application is affected only if it explicitly opts a FileUrl (ImageUrl, AudioUrl, VideoUrl, DocumentUrl) into force_download='allow-local' on a URL influenced by untrusted input; it is not affected when using bundled integrations to ingest user input (Agent.to_web / clai web, VercelAIAdapter, AGUIAdapter / Agent.to_ag_ui), since they do not propagate force_download from external data, nor when downloading only from developer-controlled URLs. This issue has been fixed in version 1.99.0.", "A flaw was found in Pydantic AI, a Python agent framework for building Generative AI applications. When an application is configured to allow local file downloads from untrusted URLs, a Server-Side Request Forgery (SSRF) vulnerability exists. This flaw allows an attacker to bypass existing security controls by encoding cloud metadata IP addresses using IPv4-mapped IPv6 formats. Successful exploitation could lead to the exposure of sensitive cloud Identity and Access Management (IAM) short-term credentials." ],
  "package_state" : [ {
    "product_name" : "Lightspeed Core",
    "fix_state" : "Not affected",
    "package_name" : "lightspeed-core/lightspeed-stack-rhel9",
    "cpe" : "cpe:/a:redhat:lightspeed_core"
  }, {
    "product_name" : "Red Hat Enterprise Linux AI (RHEL AI) 3",
    "fix_state" : "Not affected",
    "package_name" : "rhelai3/bootc-cuda-rhel9",
    "cpe" : "cpe:/a:redhat:enterprise_linux_ai:3"
  }, {
    "product_name" : "Red Hat Enterprise Linux AI (RHEL AI) 3",
    "fix_state" : "Not affected",
    "package_name" : "rhelai3/bootc-gaudi-rhel9",
    "cpe" : "cpe:/a:redhat:enterprise_linux_ai:3"
  }, {
    "product_name" : "Red Hat Enterprise Linux AI (RHEL AI) 3",
    "fix_state" : "Not affected",
    "package_name" : "rhelai3/bootc-rocm-rhel9",
    "cpe" : "cpe:/a:redhat:enterprise_linux_ai:3"
  }, {
    "product_name" : "Red Hat Enterprise Linux AI (RHEL AI) 3",
    "fix_state" : "Not affected",
    "package_name" : "rhelai3/disk-image-cuda-rhel9",
    "cpe" : "cpe:/a:redhat:enterprise_linux_ai:3"
  } ],
  "references" : [ "https://www.cve.org/CVERecord?id=CVE-2026-46678\nhttps://nvd.nist.gov/vuln/detail/CVE-2026-46678\nhttps://github.com/pydantic/pydantic-ai/releases/tag/v1.99.0\nhttps://github.com/pydantic/pydantic-ai/security/advisories/GHSA-cqp8-fcvh-x7r3" ],
  "name" : "CVE-2026-46678",
  "csaw" : false
}