CVE-2026-133505: pydantic-ai · Type Confusion
Affects pydantic-aiSource CVE Database V5
Not known to be exploited · CVSS 5.9 Medium · patch available : update pydantic-ai when convenient.
Data as of 20 Nov 2026, 07:57 UTC
Thin evidence
One scorer or none| CNA (Pydantic) | CVSS 3.1 | 5.9 |
|---|
- Patch
- Available
CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:N/A:NExploitation evidence
Disclosed: evidence found.
CVE published 20 Nov 2026
Detectable: no evidence on record.
No public nuclei template indexed
Weaponized: no evidence on record.
No public exploit code indexed in Metasploit or Exploit-DB
Exploited in the wildExploited: no evidence on record.
Not in CISA KEV and no source reports exploitation
Observed by OffSeq MirageSeen by Mirage: no evidence on record.
No attack traffic recorded by OffSeq Mirage sensors
A missing step is not evidence of safety. Sources: cve.org (opens in a new tab), the Metasploit, Exploit-DB and nuclei-templates index as of 19 Nov 2026.
What to do
Affected software
| Product | Affected | Fixed in |
|---|---|---|
| pydanticpydantic-ai | Affected
| Fixed in– |
| pydanticpydantic-ai | Affected
| Fixed in– |
| pydanticpydantic-ai-slim | Affected
| Fixed in– |
| pydanticpydantic-ai-slim | Affected
| Fixed in– |
PyPIpydantic-aipkg:pypi/pydantic-aiOther threats | Affected
| Fixed in– |
PyPIpydantic-ai-slimpkg:pypi/pydantic-ai-slimOther threats | Affected
| Fixed in– |
Check your own hosts for these packages with threat-finder (opens in a new tab), our free open-source scanner.
AI-suggested
This vulnerability is fixed in pydantic-ai versions 1.107.10 and 2.66.0. Users should upgrade to these or later versions to remediate the issue. Since this is a cloud service, the vendor manages remediation for the cloud-hosted service; users should verify with the vendor advisory for confirmation. No additional mitigation is indicated.
Description
CVE-2026-133505 is a type confusion vulnerability in pydantic-ai that occurs when message history containing tool results with JSON objects shaped like Pydantic AI file types is serialized and reloaded. This can allow a third party controlling returned data to cause the application to download URLs on its local network or access files such as s3:// objects using the application's credentials. The vulnerability affects applications that deserialize third-party data in tool results and use certain Pydantic AI model providers that download files or resolve non-HTTP URLs. The issue is fixed in pydantic-ai versions 1.107.10 and 2.66.0.