What’s Vulnerable › Vulnerabilities
CVE-2026-54249: VercelAIAdapter trusts client-controlled `providerMetadata` to construct `UploadedFile` — S3/GCS confused deputy via provider metadata injection
- Severity: medium (CVSS 6.8 v3.1)
- Exploited in the wild: not listed in CISA KEV
- EPSS: 0.3% probability of exploitation in the next 30 days
- Public exploit or detection template: none known
- Published: 2026-07-29 · updated 2026-08-04
- Weakness: CWE-918
Description
Pydantic AI is a Python agent framework for building Generative AI applications. In versions 1.65.0 through 1.105.0, and 2.0.0b1 through 2.0.0b5, a client that submits message history to a Pydantic AI UI adapter (such as the Vercel AI adapter) can reference arbitrary files in the application's model-provider or cloud-storage account. While file URL parts are validated against a scheme allowlist, UploadedFile references — which point to a file by provider file ID or cloud-storage URI (e.g. s3://…, gs://…) — were forwarded without validation. Because the provider resolves an UploadedFile using the server-side identity (IAM role, service account, or provider API key) rather than the client's, an attacker can craft message history to make the server read objects from its own account or other tenants, given a referenceable identifier. Exploitation requires a valid file identifier, which is not always unguessable depending on how the application names objects. This issue has been fixed in versions 1.106.0 and 2.0.0b6.
Affected products
- pydantic-ai: from 1.65.0 before 1.105.0; 2.0.0-beta1, 2.0.0-beta2, 2.0.0-beta3, 2.0.0-beta4, 2.0.0-beta5 — fixed in 1.105.0
How to fix
Upgrade to a fixed version: pydantic-ai 1.105.0. Check the vendor advisory for mitigations.
References
Get alerted when CVE-2026-54249 or the next vulnerability affects your stack