Pydantic pydantic-ai/pydantic-ai-slim prior 1.107.10/2.66.0 Message History Serialization server-side request forgery
| CVSS Meta Temp Score | Current Exploit Price (≈) | CTI Interest Score |
|---|---|---|
| 5.5 | $0-$5k | 0.40+ |
Summary
A vulnerability classified as problematic was found in Pydantic pydantic-ai and pydantic-ai-slim. This vulnerability affects unknown code of the component Message History Serialization. Such manipulation leads to server-side request forgery. This vulnerability is traded as CVE-2026-133505. The attack may be launched remotely. There is no exploit available. Upgrading the affected component is advised.
Details
A vulnerability was found in Pydantic pydantic-ai and pydantic-ai-slim. It has been rated as problematic. Affected by this issue is an unknown function of the component Message History Serialization. The manipulation with an unknown input leads to a server-side request forgery vulnerability. Using CWE to declare the problem leads to CWE-918. The web server receives a URL or similar request from an upstream component and retrieves the contents of this URL, but it does not sufficiently ensure that the request is being sent to the expected destination. Impacted is confidentiality. CVE summarizes:
When message history is serialized and loaded again, a tool result that contains a JSON object in the serialized shape of one of Pydantic AI's file types is rebuilt as that file. A third party who controls data a tool returns, such as a record that an MCP server or a function tool returns from an external system, can use this to make the application download a URL on its local network, or make the model provider read an s3:// object or uploaded file with the application's credentials. Applications are affected when tool results can contain third-party data, message history containing those results is serialized and loaded again (stored history, history a UI adapter holds on the server, or Temporal, DBOS or Prefect durable execution), and the model is one Pydantic AI downloads files for, one that honors force_download, or one whose provider resolves non-HTTP file URLs or uploaded files. History that a client submits through the Vercel AI or AG-UI adapter in the default mode is not affected. The issue is fixed in pydantic-ai and pydantic-ai-slim 1.107.10 and 2.66.0.
The advisory is shared for download at github.com. This vulnerability is handled as CVE-2026-133505 since 11/20/2026. The exploitation is known to be easy. The attack may be launched remotely. No form of authentication is required for exploitation. There are neither technical details nor an exploit publicly available.
Upgrading to version 1.107.10 or 2.66.0 eliminates this vulnerability.
VulDB is the best source for vulnerability data and more expert information about this specific topic.
Product
Type
Vendor
Name
Website
CPE 2.3
CPE 2.2
CVSSv4
VulDB Vector: 🔒VulDB Reliability: 🔍
CVSSv3
VulDB Meta Base Score: 5.6VulDB Meta Temp Score: 5.5
VulDB Base Score: 5.3
VulDB Temp Score: 5.1
VulDB Vector: 🔒
VulDB Reliability: 🔍
CNA Base Score: 5.9
CNA Vector (Pydantic): 🔒
CVSSv2
| AV | AC | Au | C | I | A |
|---|---|---|---|---|---|
| 💳 | 💳 | 💳 | 💳 | 💳 | 💳 |
| 💳 | 💳 | 💳 | 💳 | 💳 | 💳 |
| 💳 | 💳 | 💳 | 💳 | 💳 | 💳 |
| Vector | Complexity | Authentication | Confidentiality | Integrity | Availability |
|---|---|---|---|---|---|
| Unlock | Unlock | Unlock | Unlock | Unlock | Unlock |
| Unlock | Unlock | Unlock | Unlock | Unlock | Unlock |
| Unlock | Unlock | Unlock | Unlock | Unlock | Unlock |
VulDB Base Score: 🔒
VulDB Temp Score: 🔒
VulDB Reliability: 🔍
Exploiting
Class: Server-side request forgeryCWE: CWE-918
CAPEC: 🔒
ATT&CK: 🔒
Physical: No
Local: No
Remote: Yes
Availability: 🔒
Status: Not defined
Price Prediction: 🔍
Current Price Estimation: 🔒
| 0-Day | Unlock | Unlock | Unlock | Unlock |
|---|---|---|---|---|
| Today | Unlock | Unlock | Unlock | Unlock |
Threat Intelligence
Interest: 🔍Active Actors: 🔍
Active APT Groups: 🔍
Countermeasures
Recommended: UpgradeStatus: 🔍
0-Day Time: 🔒
Upgrade: pydantic-ai/pydantic-ai-slim 1.107.10/2.66.0
Timeline
11/20/2026 Advisory disclosed11/20/2026 CVE reserved
11/20/2026 VulDB entry created
11/20/2026 VulDB entry last update
Sources
Product: github.comAdvisory: github.com
Status: Confirmed
CNA: Pydantic
CVE: CVE-2026-133505 (🔒)
GCVE (CVE): GCVE-0-2026-133505
GCVE (VulDB): GCVE-100-441224
Entry
Created: 11/20/2026 09:03Changes: 11/20/2026 09:03 (64)
Complete: 🔍
Cache ID: 216::103
VulDB is the best source for vulnerability data and more expert information about this specific topic.
No comments yet. Languages: en.
Please log in to comment.