CVE-2026-54249 Pydantic AI: Unvalidated UploadedFile references in UI adapters allow server-side file access using the application's credentials
Attackers can inject provider metadata to force the server to read arbitrary files from cloud storage using server-side credentials.
- Exploited in the wild
- Not known
- Login needed
- Not needed
- Attackable
- Over the internet
- Victim action needed
- Not needed
- Fix
- Available
What is CVE-2026-54249?
CVE-2026-54249 is a medium-severity server-side request forgery vulnerability in pydantic-ai, published on 29 Jul 2026. An attacker can exploit it over the internet without logging in, with no action from the victim.
Official 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.
Weakness: CWE-918
Which versions are affected by CVE-2026-54249?
10 open source packages ship an affected version, including pydantic-ai and pydantic-ai-slim. It affects 1 product.
| Package | Affected | Fixed in |
|---|---|---|
pydantic-ai PyPI | From 1.65.0 | 1.106.0, 2.0.0b6 |
pydantic-ai PyPI | From 1.65.0 | 1.106.0 |
pydantic-ai PyPI | From 1.65.0 | 1.106.0 |
pydantic-ai PyPI | From 2.0.0b1 | 2.0.0b6 |
pydantic-ai PyPI | From 2.0.0b1 | 2.0.0b6 |
pydantic-ai-slim PyPI | From 1.65.0 | 1.106.0, 2.0.0b6 |
4 more packages
pydantic-ai-slim PyPI | From 1.65.0 | 1.106.0 |
pydantic-ai-slim PyPI | From 1.65.0 | 1.106.0 |
pydantic-ai-slim PyPI | From 2.0.0b1 | 2.0.0b6 |
pydantic-ai-slim PyPI | From 2.0.0b1 | 2.0.0b6 |
Products include Pydantic Pydantic Ai.
How do I fix CVE-2026-54249?
Upgrade pydantic-ai to a fixed version for your release line: 1.106.0 or 2.0.0b6.
Upgrade, and send outbound requests through an allow-list that blocks internal addresses. More about Server-side request forgery.
Is CVE-2026-54249 being exploited?
There is no known exploitation of CVE-2026-54249 in the wild and no public exploit code.
Other vulnerabilities in pydantic-ai
- CVE-2026-25580 Pydantic AI Affected by Server-Side Request Forgery (SSRF) in URL Download Handling
- CVE-2026-107295 Pydantic AI Web chat UI (`Agent.to_web()`, `clai web`): a website visited by the developer can trigger agent runs and server-side tool execution on the local chat endpoint
- CVE-2026-107286 Pydantic AI: Concurrency-limited models can keep their slot when a streamed request ends early
- CVE-2026-25640 Pydantic AI affected by Stored XSS via Path Traversal in Web UI CDN URL
- CVE-2026-107289 Pydantic AI: SSRF cloud-metadata blocklist bypass via IPv6 zone identifiers
Sources
Also known as GHSA-h7p7-w5gc-xj3w, PYSEC-2026-3692, PYSEC-2026-3693.