Skip to main content
CVE-2026-133505VulnerabilityPublished

When message history is serialized and loaded again, a tool result that contains a JSON object in the serialized shape

Source GCVE Database

0
Compare
Authoritative record:CVE-2026-133505· Medium 5.9

Not known to be exploited · CVSS 5.9 Medium · patch available : update pydantic-ai when convenient.

Data as of 20 Nov 2026, 11:05 UTC

CVSS 3.1 base score
5.9Medium
How severe the flaw is on the 0–10 CVSS scale.

Thin evidence

One scorer or none
CVSS scores by source
CNA (Pydantic)CVSS 3.15.9
Patch
Available
CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:N/A:N

Exploitation evidence

  1. Disclosed: evidence found.

    CVE published 20 Nov 2026

  2. Detectable: no evidence on record.

    No public nuclei template indexed

  3. Weaponized: no evidence on record.

    No public exploit code indexed in Metasploit or Exploit-DB

  4. Exploited in the wild: no evidence on record.

    Not in CISA KEV and no source reports exploitation

  5. Observed by OffSeq 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

ProductAffectedFixed in
pydanticpydantic-aiAffected
  • >=1.50.0 <=1.107.9
Fixed in–
pydanticpydantic-aiAffected
  • >=2.0.0b1 <=2.65.0
Fixed in–
pydanticpydantic-ai-slimAffected
  • >=1.50.0 <=1.107.9
Fixed in–
pydanticpydantic-ai-slimAffected
  • >=2.0.0b1 <=2.65.0
Fixed in–
PyPIpydantic-aipkg:pypi/pydantic-aiOther threatsAffected
  • >=1.50.0 <=1.107.9
  • >=2.0.0b1 <=2.65.0
Fixed in–
PyPIpydantic-ai-slimpkg:pypi/pydantic-ai-slimOther threatsAffected
  • >=1.50.0 <=1.107.9
  • >=2.0.0b1 <=2.65.0
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 and pydantic-ai-slim versions 1.107.10 and 2.66.0. Users should upgrade to these or later versions to remediate the issue. No other mitigations are specified or required if the fix is applied.

Description

This vulnerability involves the serialization and reloading of message history containing tool results with JSON objects shaped like Pydantic AI file types. An attacker controlling third-party data returned by a tool can exploit this to cause the application to download internal URLs or access files using the application's credentials. The issue affects applications that deserialize such tool results from stored or server-held history when using certain Pydantic AI versions. The vulnerability is fixed in pydantic-ai and pydantic-ai-slim versions 1.107.10 and 2.66.0.

References

Community reviews

Loading reviews…