Skip to content
Fencer Vulns
medium 6.8

CVE-2026-54249 json

VercelAIAdapter trusts client-controlled `providerMetadata` to construct `UploadedFile` — S3/GCS confused deputy via provider metadata injection

published 2026-07-29 3 mo ago modified 2026-08-19 2 mo ago also GHSA-h7p7-w5gc-xj3w , PYSEC-2026-3692 , PYSEC-2026-3693 , EUVD-2026-50562

cvss
6.8
version 3.1, CNA
cisa kev
Not listed
not in CISA's catalog
epss
0.3%
EPSS 0.3% chance of exploitation in 30 days, percentile 24%
public exploits
0
none known

Summary

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.

Patch / fix

  • pypi pydantic-ai-slim 1.106.0, 2.0.0b6
  • pypi pydantic-ai 1.106.0, 2.0.0b6
  • pydantic pydantic_ai 1.105.0

Vendor advisories

What the vendors themselves say about their products: affected, fixed or not affected, and what to do.

red hat product security vex CVE-2026-54249 updated cvss 6.8

pydantic-ai: Pydantic AI: Information disclosure through unvalidated file references.

  • Red Hat Lightspeed Core lightspeed-core/lightspeed-stack-rhel9 Red Hat Enterprise Linux AI (RHEL AI) 3 rhelai3/bootc-cuda-rhel9, rhelai3/bootc-rocm-rhel9, rhelai3/bootc-gaudi-rhel9, rhelai3/disk-image-cuda-rhel9
    not affected: vulnerable code not present

Red Hat CSAF VEX © Red Hat, Inc., from https://security.access.redhat.com/data/csaf/v2/vex/; changed: reduced to product statuses and remediations. CC BY 4.0 · csaf

CISA SSVC

Exploitation
none
Automatable
no
Technical impact
partial
Assessed
3 mo ago

Exploit prediction

0.32% chance of exploitation in the next 30 days, higher than 24% of all scored CVEs (FIRST EPSS, 2026-11-08).

CVSS scores

assigned by version score vector
CNA 3.1 6.8 CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:C/C:H/I:N/A:N
OSV 3.1 6.8 CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:C/C:H/I:N/A:N
GitHub 3.1 6.8 CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:C/C:H/I:N/A:N

Affected packages

ecosystem package affected fixed in
pypi pydantic-ai-slim
>=1.65.0, <1.106.0
>=2.0.0b1, <2.0.0b6
1.106.0
2.0.0b6
pypi pydantic-ai
>=1.65.0, <1.106.0
>=2.0.0b1, <2.0.0b6
1.106.0
2.0.0b6

Affected products

  • pydantic pydantic-ai
  • pydantic pydantic-ai-slim

Classification

Weakness
  • CWE-918 Server-Side Request Forgery

References

Sources

Fencer Vulns keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.