HIGH · 8.6

CVE-2026-25580

Pydantic AI is a Python agent framework for building applications and workflows with Generative AI. From 0.0.26 to before 1.56.0, aServer-Side Request Forgery (SSRF) vulnerability exists in Pydantic A...

Vulnerability Description

Pydantic AI is a Python agent framework for building applications and workflows with Generative AI. From 0.0.26 to before 1.56.0, aServer-Side Request Forgery (SSRF) vulnerability exists in Pydantic AI's URL download functionality. When applications accept message history from untrusted sources, attackers can include malicious URLs that cause the server to make HTTP requests to internal network resources, potentially accessing internal services or cloud credentials. This vulnerability only affects applications that accept message history from external users. This vulnerability is fixed in 1.56.0.

CVSS Score

8.6

HIGH

CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:N/A:N
Attack Vector
NETWORK
Attack Complexity
LOW
Privileges Required
NONE
User Interaction
NONE
Scope
CHANGED
Confidentiality
HIGH
Integrity
NONE
Availability
NONE

Affected Products

VendorProductVersions
PydanticPydantic Ai>= 0.0.26, < 1.56.0

Related Weaknesses (CWE)

References

FAQ

What is CVE-2026-25580?

CVE-2026-25580 is a vulnerability with a CVSS score of 8.6 (HIGH). Pydantic AI is a Python agent framework for building applications and workflows with Generative AI. From 0.0.26 to before 1.56.0, aServer-Side Request Forgery (SSRF) vulnerability exists in Pydantic A...

How severe is CVE-2026-25580?

CVE-2026-25580 has been rated HIGH with a CVSS base score of 8.6/10. Review the CVSS metrics above for detailed severity breakdown.

Is there a patch for CVE-2026-25580?

Check the references section above for vendor advisories and patch information. Affected products include: Pydantic Pydantic Ai.