CVE-2026-48782 is a medium-severity (CVSS 6.8) Server-Side Request Forgery (SSRF) vulnerability in pydantic-ai-slim. O3 Security confirms whether CVE-2026-48782 is actually reachable in your code before you act, and blocks exploitation at runtime until you patch.
pydantic-ai: SSRF blocklist bypass via IPv4-compatible, SIIT/IVI, and local NAT64 IPv6 addresses (incomplete fix of CVE-2026-46678)
Real-World Exposure
pydantic-ai-slim🐍pydantic-ai🐍pydantic-ai🐍pydantic-ai-slimReal-time download stats are indexed for npm and PyPI packages. This vulnerability affects PyPI packages — download data is not available via public APIs for these ecosystems.
Description
Pydantic AI is a Python agent framework for building applications and workflows with Generative AI. In versions 1.56.0 through 1.101.0, 2.0.0b1, and 2.0.0b2, the cloud-metadata blocklist could be bypassed by encoding the metadata IP in an IPv6 transition form that the previous fix, CVE-2026-46678, did not decode, exposing cloud IAM short-term credentials. The previous remediation decoded only IPv4-mapped IPv6, 6to4, and the NAT64 well-known prefix, so the metadata guarantee did not hold for the remaining transition forms: IPv4-compatible IPv6 (::a.b.c.d), the NAT64 RFC 8215 local-use prefix (64:ff9b:1::/48), operator-chosen NAT64 prefixes, and ISATAP. The IPv6 wrapper is then delivered to the underlying IPv4 metadata endpoint. This occurs when an application using Pydantic AI opts a URL into force_download='allow-local' (which disables the default block on private/internal IPs) and runs on a network that actually routes the affected IPv6 transition forms: NAT64-configured networks (IPv6-only or dual-stack-with-NAT64 deployments, including some Kubernetes setups) for the NAT64 variants, or networks with an ISATAP tunnel for ISATAP. A standard dual-stack cloud VM or container does not route these forms and is not affected in practice. The IPv4-compatible and Teredo variants are deprecated and addressed as defense-in-depth. This is an incomplete fix of GHSA-cqp8-fcvh-x7r3 / CVE-2026-46678 (itself a follow-up to CVE-2026-25580). This issue has been fixed in version 2.0.0b3.
Affected Packages
| Ecosystem | Package | Vulnerable range | Fix |
|---|---|---|---|
| 🐍PyPI | pydantic-ai-slim | ≥ 1.56.0&&< 1.102.0 | 1.102.0 |
| 🐍PyPI | pydantic-ai | ≥ 1.56.0&&< 1.102.0 | 1.102.0 |
| 🐍PyPI | pydantic-ai | ≥ 2.0.0b1&&< 2.0.0b3 | 2.0.0b3 |
| 🐍PyPI | pydantic-ai-slim | ≥ 2.0.0b1&&< 2.0.0b3 | 2.0.0b3 |
Detection & mitigation playbook
Open-source dependencyDetect
Scan your dependency tree (package-lock.json, pnpm-lock.yaml, requirements.txt, go.sum, etc.) for pydantic-ai-slim. O3's reachability analysis confirms whether the vulnerable code path is actually invoked in your application, so you act on real exposure instead of every transitive match.
Fix
Update pydantic-ai-slim to 1.102.0 or later, then make sure no transitive (indirect) dependency still pins the vulnerable range — O3 confirms CVE-2026-48782 is resolved across your whole dependency graph.
Workarounds
If you can't upgrade right away: gate or disable the affected feature, validate untrusted input at the boundary, and avoid passing attacker-controlled data into the vulnerable path. O3's runtime protection blocks exploitation in production as an interim safeguard until the upgrade lands.
How O3 protects you
O3 pinpoints whether CVE-2026-48782 is reachable in your code and exactly where to fix it, then blocks exploitation in production at runtime until the patched version is deployed.
Tailored to CVE-2026-48782. Runtime protection reduces exposure until a permanent patch is applied and verified — it complements patching, it doesn't replace it.
Frequently Asked Questions
Is CVE-2026-48782 in your dependencies?
O3 detects CVE-2026-48782 across PyPI dependencies and uses function-level reachability to confirm whether the vulnerable code path is actually reachable — not just present. No false positives.