CVE Tools
Track your stack

CVE-2026-54249

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

No known exploitation. EPSS puts it in the 23rd percentile. A vendor fix is available.

CVSS 3.16.8MediumEPSS percentile23rd0.3% chance in 30 daysCISA KEVNot listedNo confirmed exploitation
No public exploit knownFixVendor fixNo build named by the sources

Published Updated Sources: CVE.org, NVD

NVD CVE.org

What to do

The vendor has published a fix. Version details are below where the sources state them.

  • Pydantic-aiAffected: >= 1.65.0, < 1.106.0Upgrade to: not statedAffected: >= 2.0.0b1, < 2.0.0b6Upgrade to: not statedStated by: CVE record
  • Pydantic-ai-slimAffected: >= 2.0.0b1, < 2.0.0b6Upgrade to: not statedAffected: >= 1.65.0, < 1.106.0Upgrade to: not statedStated by: CVE record

Versions as the sources state them. Full version matrix after sign-in

What it is

From the CVE record

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.

In plain language

No plain-language summary for this CVE yet.

Exploitation

Where each signal puts this CVE on the scale from published to confirmed exploited.

EPSS23rd
CISA KEV

Not in the catalog. CISA has not confirmed exploitation.

Public exploits

No public exploit or proof of concept found in the sources we track.

EPSS

0.3% chance of exploitation activity in the next 30 days, which ranks it in the 23rd percentile of scored CVEs.

Exploit Prediction Scoring System, FIRST.org. A probability, not a confirmation.

Lifecycle

8 events over 6 days, from the signal feeds we watch.

  1. Patch availablerecord updated
  2. Record updatedrecord updated
  3. Publishedweakness classified, att&ck mapped, record updated

Affected products

Technical detail

CVSS 3.1 vector

Open in the CVSS calculator

CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:C/C:H/I:N/A:N

Scored 6.8 by NVD.

How it is reached

  • Attack Vector NetworkExploitable remotely over the network without any special conditions
  • Attack Complexity HighRequires specific conditions like a race condition or non-default configuration
  • Privileges Required NoneNo authentication required — anyone can exploit this
  • User Interaction NoneNo user interaction needed — fully automated exploitation

Scope

  • Scope ChangedThe exploit can affect other components (e.g. sandbox escape, host compromise from VM)

Impact if exploited

  • Confidentiality HighTotal information disclosure — all data in the component is compromised
  • Integrity NoneNo integrity impact
  • Availability NoneNo availability impact

Weaknesses

ATT&CK techniques

Mapped from the weaknesses above (CWE to ATT&CK), not observed in attacks.

Sources

References in the record

Watch the software you run.

My Stack ranks new CVEs for your products by real-world exploitation, so the next serious one reaches you without reading every advisory.

We'll flag the next CVE, public exploit or patch for Pydantic Ai, not every advisory.