HighVulnerability

CVE-2026-25580: Pydantic AI server-side request forgery in URL download via message history

Source: NVD(opens in a new tab)
Identifier: CVE-2026-25580
Published: February 6, 2026
Record updated: October 9, 2026

Affected: pydantic-ai >= 0.0.26, < 1.56.0
pydantic-ai-slim >= 0.0.26, < 1.56.0
Fixed in: 1.56.0
pydantic-ai 1.56.0 released February 5, 2026, on the day of disclosure
pydantic-ai-slim 1.56.0 released February 5, 2026, on the day of disclosure
Known exploitation: Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
EPSS: 0.6%

Summary

Pydantic AI, a Python agent framework for Generative AI applications, contains a Server-Side Request Forgery (SSRF) flaw in its URL download functionality in versions from 0.0.26 to before 1.56.0. When applications accept message history from untrusted sources, attackers can include malicious URLs that make the server send HTTP requests to internal network resources, potentially reaching internal services or cloud credentials. Only applications that accept message history from external users are affected.

Mitigation

This vulnerability is fixed in 1.56.0.

Details

Scores and exploitation

CVSS score: 8.6(high)
Patch available: Yes
EPSS: 0.6%Estimated probability that this CVE is exploited in the next 30 days, from the FIRST Exploit Prediction Scoring System. Read on November 4, 2026.

Weaknesses and techniques

Weakness (CWE): CWE-918
Attack pattern (CAPEC): CAPEC-664

Affected

Packages: pydantic-ai@>= 0.0.26, < 1.56.0 (fixed: 1.56.0)
pydantic-ai-slim@>= 0.0.26, < 1.56.0 (fixed: 1.56.0)

Classification

Attack type: Other
Attack sophistication: Moderate
AI component targeted: Agent
Impact: Confidentiality
Labels: security

How this record was produced

Summaries, mitigations and labels on this page are generated automatically from the source. The linked source is authoritative. The source gives this advisory a description and no title, so the title above is a headline generated from the source text.

Original source: https://nvd.nist.gov/vuln/detail/CVE-2026-25580

First tracked: February 15, 2026 at 08:53 PM ET, from NVD/CVE Database

Classifier: claude-haiku-5-5, prompt v4

Classifier confidence: 93% (self-assessed)

Affected packages in the Exposure Registry

Matched by package name and ecosystem. Each entry shows whether the package delegates to a language model and how many tracked packages depend on it.

pydantic-aiPyPILLM dependency since 2024-05-20 · 4 tracked dependents
pydantic-ai-slimPyPILLM dependency since 2024-11-25 · 7 tracked dependents

Topics

AI agents

Summary

Mitigation

Affected packages in the Exposure Registry

Topics

Related items