LiveActive security incident?Get immediate response
CVE Record

CVE-2026-25580: Pydantic AI Affected by Server-Side Request Forgery (SSRF) in URL Download Handling

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.

HighCVSS 8.6Not KEV-listedUpdated
Discuss exposureBack to CVEs
Glexia's TakeAutomated analysishigh

Security readout for executives and security teams

Plain-English summary

Pydantic AI versions 0.0.26 through before 1.56.0 can be tricked into making server-side web requests when untrusted users supply message history containing URLs. In exposed applications, this could let an attacker reach internal services or cloud credential endpoints through the application server.

Executive priority

Prioritize remediation for internet-facing AI workflows that ingest user-provided conversation history. The business risk is confidential internal data exposure, not service disruption, and the fix is identified as upgrading to 1.56.0.

Technical view

This is a CWE-918 SSRF in Pydantic AI URL download handling. The advisory scope is limited to applications that accept message history from external or untrusted users. The CVSS 3.1 score is 8.6 because exploitation is network reachable, unauthenticated, low complexity, and can expose high-confidentiality internal data.

Likely exposure

Exposure is limited to Python applications using pydantic-ai >=0.0.26 and <1.56.0 that accept externally supplied message history. Internal-only uses or applications that do not accept untrusted message history are not described as affected by the source bundle.

Exploitation context

The provided sources do not show CISA KEV listing or active exploitation. The risk comes from attacker-controlled URLs causing server-side requests to internal network resources, potentially including cloud metadata or internal services.

Researcher notes

Do not broaden scope beyond pydantic-ai and the untrusted message-history condition. Evidence supports SSRF and high confidentiality impact, but does not cite public exploitation, affected downstream products, or additional vendor mitigations beyond the fixed version.

Mitigation direction

  • Upgrade pydantic-ai to version 1.56.0 or later.
  • Identify applications accepting message history from external users.
  • Follow the Pydantic advisory and commit guidance for remediation details.
  • Restrict or disable URL download behavior for untrusted message history where feasible.
  • Review outbound network controls for access to internal services and metadata endpoints.

Validation and detection

  • Inventory deployed pydantic-ai versions across services and build artifacts.
  • Confirm affected services do or do not accept external message history.
  • Verify upgraded deployments run pydantic-ai 1.56.0 or later.
  • Review logs for unexpected server-side outbound requests to internal addresses.
  • Check dependency lockfiles and container images for vulnerable versions.
Prepared
Confidence
high
Sources
7

Public sources used

Generated from the cited source records. This long-tail analysis has not been individually reviewed by a named human.

Potential ATT&CK relevance

Conservative CVE-to-ATT&CK context

These mappings and lookup hints may be relevant to the vulnerability behavior, CWE, affected product, or exposure path. Glexia-inferred context is not an official MITRE, ATT&CK, CWE, or CVE Program mapping.

ATT&CK lookup starting points

Use these exact CWE pages and searches to review the Glexia ATT&CK library from this CVE's weakness and description context.

cwe · medium confidence lookup

CWE-918: Information exposure and cloud metadata lookup

Information exposure and SSRF weaknesses can make discovery, cloud metadata, and credential material review relevant. Open the exact CWE lookup page first, then review the ATT&CK searches from that MITRE weakness context. This is a Glexia lookup hint, not an official ATT&CK mapping.

Open ATT&CK lookup
description · low confidence lookup

Cloud metadata behavior lookup

The CVE wording references SSRF or metadata access, so cloud discovery and credential material review may help. This is a Glexia inferred lookup path, not an official MITRE, ATT&CK, or CVE Program mapping.

Open ATT&CK lookup
cve · low confidence lookup

CVE-2026-25580 mapping review

Open the CVE-to-ATT&CK bridge for reviewed, inferred, or future official mappings tied to this CVE.

Open ATT&CK lookup
Vulnerability profileCVE Program record
Severity
High
CVSS
8.6 (3.1)
Known Exploited
No
Published

Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:N/A:N

Official CVE source material

CNA and ADP enrichment extracted from CVE v5

These fields come from the CVE record and ADP containers, not from Glexia's Take. They preserve time-varying source decisions such as CISA SSVC, KEV status, CVSS metrics, and provider references.

2CVSS vectors
5Timeline events
2ADP providers
6Source links

SSVC decision data

CISA-ADPCISA Coordinator
Timestamp
Version
2.0.3
Exploitation: noneAutomatable: yesTechnical Impact: partial

CVSS vector scores

2 official scores

We collect every scored CVSS vector available in the official CNA and ADP containers. When more than one version is present, the table keeps the source vectors side by side instead of collapsing them into the highest score.

ScoreVersionSeverityVectorExploitImpactSource
8.6CVSS 3.1HighCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:N/A:N3.94GitHub_M
8.6CVSS 3.1HighCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:N/A:N3.94redhat-SADP

Vulnerability scoring details

Base CVSS 3.1 score

8.6High
CVSS 3.1 vector shape for CVE-2026-25580Attack VectorAttack ComplexityPrivileges RequiredUser InteractionScopeConfidentiality ImpactIntegrity ImpactAvailability Impact

Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:N/A:N

Attack Vector
NetworkAdjacentLocalPhysical
Attack Complexity
LowHigh
Privileges Required
NoneLowHigh
User Interaction
NoneRequired
Scope
ChangedUnchanged
Confidentiality Impact
HighLowNone
Integrity Impact
HighLowNone
Availability Impact
HighLowNone

Vulnerability timeline

Timeline events are normalized from CVE metadata, CNA source timelines, ADP timelines, and KEV metadata when present.

  1. CVE reservedCVE Program

    The CVE ID was reserved by the assigning CNA.

  2. ADP timelineredhat-SADP

    Made public.

  3. CVE publishedCVE Program

    The CVE record was published.

  4. ADP timelineredhat-SADP

    Reported to Red Hat.

  5. CVE updatedCVE Program

    The CVE record metadata indicates this as the latest update time.

ADP provider summaries

CISA-ADPCISA ADP Vulnrichment
other:ssvc
redhat-SADPPydantic AI: Pydantic AI: Information disclosure via Server-Side Request Forgery (SSRF) through malicious URLs in message history.
other:Red Hat severity ratingcvssV3_1
  • 2026-02-09T11:05:31.886Z: Reported to Red Hat.
  • 2026-02-06T21:01:38.035Z: Made public.

Source materials

Affected products

Products and packages named in the record

VendorProductVersion / packageStatus
pydanticpydantic-ai>= 0.0.26, < 1.56.0Listed
Weakness

CWE details

CWE-918

CWE links open Glexia weakness intelligence pages with official CWE context, developer remediation guidance, and related CVE mappings.

CWE-918 · source CWE mapping

Server-Side Request Forgery (SSRF)

Server-Side Request Forgery (SSRF) represents a recurring weakness pattern that can create exploitable paths when design, validation, or implementation controls are missing.

Open CWE intelligenceSame-CWE CVEs