Raw vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:N/A:NCVSS and EPSS are reproduced from their sources (NVD, FIRST EPSS). Risk Priority is our own derived reading, not an NVD score.
Summary
CVE-2026-25580 is a high-severity SSRF (CWE-918) vulnerability in Pydantic Pydantic Ai. Its CVSS base score is 8.6 (High).
Operationally, exploitation aligns with the MITRE ATT&CK technique Exploit Public-Facing Application (T1190); ranked at the 45th percentile by exploit likelihood (below the median); it is not currently listed in the CISA KEV catalog; a public proof-of-concept is referenced.
This vulnerability is AI-related — categorised as AI Agent Protocols and Integrations; in the LLM/Generative AI Risks risk domain.
The strongest mitigations our analysis identified map to AC-4 (Information Flow Enforcement) and SI-10 (Information Input Validation) — see the control section below for these in your framework.
Deeper analysis AI-assisted summary
Synthesised by an AI model from the NVD description and linked references — a reading aid, not an authoritative source.
CVE-2026-25580 is a Server-Side Request Forgery (SSRF) vulnerability, classified under CWE-918, affecting Pydantic AI, a Python agent framework for building applications and workflows with Generative AI. The issue resides in the framework's URL download functionality and impacts versions from 0.0.26 up to but not including 1.56.0. It has a CVSS v3.1 base score of 8.6 (AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:N/A:N), indicating high severity due to network accessibility, low complexity, no privileges required, and high confidentiality impact in a scoped attack.
The vulnerability can be exploited by remote attackers who submit message history containing malicious URLs to applications built with vulnerable Pydantic AI versions that accept such history from untrusted or external users. Successful exploitation causes the server to issue HTTP requests to attacker-specified internal network resources, potentially allowing access to internal services or exposure of cloud credentials. Applications not accepting external message history remain unaffected.
Mitigation is available via upgrade to Pydantic AI version 1.56.0 or later, where the vulnerability is fixed. Official advisories detail the patch in GitHub commit d398bc9d39aecca6530fa7486a410d5cce936301 and security advisory GHSA-2jrp-274c-jhv3.
This flaw highlights SSRF risks in AI agent frameworks handling untrusted inputs for Generative AI workflows, with no reported real-world exploitation as of publication on 2026-02-06.
OWASP Top 10 for Web (2025)
EU & UK References
- 🇪🇺 ENISA EUVD: EUVD-2026-5574
Vulnerability Data
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,…
more
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.
- CWE(s)
AI Security AnalysisAI
- AI Category
- AI Agent Protocols and Integrations
- Risk Domain
- LLM/Generative AI Risks
- OWASP Top 10 for LLMs 2025
- None mapped
- Classification Reason
- Matched keywords: ai, generative ai
Related Threats
MITRE ATT&CK Enterprise Techniques
CVEs Like This One
Affected Assets
Mitigating Controls
Control response
—
—
—
V1.3.6V1.5.3V5.3.2V10.4.7
Mitigating Controls (NIST 800-53 r5) AI
Information flow enforcement can restrict which destinations the server is allowed to contact on behalf of users.
Input validation directly stops untrusted URLs from being accepted and fetched without destination checks.
Boundary protection limits the network reach of server-initiated requests even if SSRF occurs.
Mitigating Controls (NIST CSF 2.0) AI
Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→CSF cross-walk (authority under review) — links open the control.
Secure development practices directly include input validation and destination allow-listing that prevent SSRF.
Runtime monitoring of web applications and services can detect anomalous outbound requests indicative of SSRF.
Vulnerability identification processes can discover and record SSRF flaws in web applications.
Network segmentation and egress controls can limit the damage from successful SSRF requests.
Mitigating Controls (ISO/IEC 27001:2022 Annex A) AI
Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→ISO cross-walk (authority under review) — links open the control.
Operational threat data describing SSRF campaigns can be used to tighten outbound-request allow-lists and detection rules before attackers exploit them.