CVE-2026-133505
Description
A flaw was found in pydantic-ai. This vulnerability can lead to unauthorized information disclosure when message history is serialized and subsequently reloaded. If tool execution results contain structured data matching internal file formats, the application automatically reconstructs them as file references instead of plain text. A remote attacker who can control data returned by external tools or services can exploit this behavior to force the application or connected artificial intelligence (AI) provider to access internal network resources or read private cloud storage objects using the application's credentials.
Statement
This vulnerability is rated as Moderate severity because exploitation requires a specific confluence of factors, including the ingestion of untrusted external tool responses, session history persistence, and backend model settings configured to resolve arbitrary URLs or cloud storage resources. Within typical enterprise deployments, applications are only exposed if custom agent workflows serialize and restore conversation states containing external data while possessing credentials to fetch internal network or cloud storage targets. Default adapter configurations prevent untrusted message histories from triggering this deserialization behavior, which limits the potential blast radius to non-standard implementations.
Mitigation
Mitigation for this issue is either not available or the currently available options do not meet the Red Hat Product Security criteria comprising ease of use and deployment, applicability to widespread installation base, or stability.
Common Vulnerability Scoring System (CVSS) Score Details
Info alert:Important note
CVSS scores for open source components depend on vendor-specific factors (e.g. version or build chain). Therefore, Red Hat's score and impact rating can be different from NVD and other vendors. Red Hat remains the authoritative CVE Naming Authority (CNA) source for its products and services (see Red Hat classifications).
The following CVSS metrics and score provided are preliminary and subject to review.
CVSS v3 Score Breakdown
| Red Hat | NVD | cve.org | |
|---|---|---|---|
| Base Score | 5.9 | N/A | 5.9 |
| Attack Vector | Network | N/A | Network |
| Attack Complexity | High | N/A | High |
| Privileges Required | None | N/A | None |
| User Interaction | None | N/A | None |
| Scope | Unchanged | N/A | Unchanged |
| Confidentiality | High | N/A | High |
| Integrity Impact | None | N/A | None |
| Availability Impact | None | N/A | None |
Vector
Red Hat: CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:N/A:N
cve.org: CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:N/A:N
Understanding the Weakness (CWE)
Integrity
Technical Impact: Modify Application Data; Unexpected State
Attackers can modify unexpected objects or data that was assumed to be safe from modification. Deserialized data or code could be modified without using the provided accessor functions, or unexpected functions could be invoked.
Availability
Technical Impact: DoS: Resource Consumption (CPU)
If a function is making an assumption on when to terminate, based on a sentry in a string, it could easily never terminate.
Other
Technical Impact: Varies by Context
The consequences can vary widely, because it depends on which objects or methods are being deserialized, and how they are used. Making an assumption that the code in the deserialized object is valid is dangerous and can enable exploitation. One example is attackers using gadget chains to perform unauthorized actions, such as generating a shell.
Frequently Asked Questions
Not sure what something means? Check out our Security Glossary.
Want to get errata notifications? Sign up here.