CVE-2026-25580
February 06, 2026
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.
Affected Packages
pydantic-ai (CONDA):
Affected version(s) >=0.0.27 <1.56.0Fix Suggestion:
Update to version 1.56.0pydantic-ai-slim (CONDA):
Affected version(s) >=0.2.14 <1.56.0Fix Suggestion:
Update to version 1.56.0https://github.com/pydantic/pydantic-ai.git (GITHUB):
Affected version(s) >=v0.0.1 <v1.56.0Fix Suggestion:
Update to version v1.56.0pydantic-ai (PYTHON):
Affected version(s) >=0.0.26 <1.56.0Fix Suggestion:
Update to version 1.56.0pydantic-ai-slim (PYTHON):
Affected version(s) >=0.0.26 <1.56.0Fix Suggestion:
Update to version 1.56.0Related Resources (4)
Do you need more information?
Contact UsCVSS v4
Base Score:
9.2
Attack Vector
NETWORK
Attack Complexity
LOW
Attack Requirements
NONE
Privileges Required
NONE
User Interaction
NONE
Vulnerable System Confidentiality
HIGH
Vulnerable System Integrity
NONE
Vulnerable System Availability
NONE
Subsequent System Confidentiality
HIGH
Subsequent System Integrity
NONE
Subsequent System Availability
NONE
CVSS v3
Base Score:
8.6
Attack Vector
NETWORK
Attack Complexity
LOW
Privileges Required
NONE
User Interaction
NONE
Scope
CHANGED
Confidentiality
HIGH
Integrity
NONE
Availability
NONE
Weakness Type (CWE)
Server-Side Request Forgery (SSRF)
EPSS
Base Score:
0.02
