VulnWatch by ve1ve2
medium 5.9 EPSS 0.70%

CVE-2026-133505: 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 re…

Source:
NVD CVE API 2.0
Published:
Fetched:
Updated:

https://nvd.nist.gov/vuln/detail/CVE-2026-133505 ↗

CWE-843CWE-918

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. References: https://github.com/pydantic/pydantic-ai/security/advisories/GHSA-4cj4-hgwf-4hc4 https://pydantic.dev/docs/ai/ui/overview/#trust-model-for-client-submitted-messages

Linked vulnerabilities (2)

CVE-2026-133505 medium 5.9 EPSS 0.70% (p54) NVDCVE.orgGHSA
CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:N/A:N

pydantic-ai: pydantic-ai-slim: pydantic-ai: Information disclosure via unsafe deserialization of tool results

CWE: CWE-502, CWE-843, CWE-918Aliases: GHSA-4cj4-hgwf-4hc4NVD: Received

Also reported by (1)