cve.bz

CVE-2026-65975 pydantic pydantic ai: Incorrect Authorization

6.5 mediumEPSS 0.3%

Medium (6.5) in pydantic pydantic ai. EPSS 0.3% estimated probability of exploitation activity in the next 30 days.

On this page
Pydantic AI is a Python agent framework for building applications and workflows with Generative AI. In versions 1.88.0 up to but not including 1.107.1 and 2.0.0b1 up to but not including 2.5.0, the UI adapters (AG-UI via Agent.to_ag_ui()/AGUIAdapter, and Vercel AI via VercelAIAdapter) use sanitize_messages to strip unresolved ("dangling") client-submitted tool calls from untrusted message history before it reaches the agent, a defense-in-depth default that prevents the agent from executing tool calls the model never emitted. However, the strip anchored to a message index computed before sanitization ran, so when a trailing client message sanitized to empty and was dropped (for example a client system message under the default manage_system_prompt='server'), a preceding assistant response carrying an unresolved tool call became the new tail and was dispatched without inspection. As a result, a remote client could cause a registered, non-approval server tool to run with client-supplied arguments rather than arguments the model produced. The impact is bounded by what the affected tools do and is most significant for applications that gate tool execution in a model-request hook (before_model_request / after_model_request), since a forged call skips the model turn and bypasses that guardrail; approval-gated tools (requires_approval=True) are not auto-executed by this path. This issue has been fixed in versions 1.107.1 and 2.5.0.

Severity

CVSS 3.1

6.5 medium
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:N
EPSS
0.3% (unchanged from 0.3% a week ago; 0.3% 30 days ago) estimated probability of exploitation activity in the next 30 days; 27th percentile. Scored 2026-11-22. A forecast for this CVE across the internet, not for your own systems.
CISA's assessment (SSVC)
Exploitation: none · Automatable: yes · Technical impact: partial, assessed 2026-07-30. From CISA's Vulnrichment in the CVE List: whether it is exploited, whether exploiting it can be automated, and how much control it gives.
CWE
CWE-863 Incorrect Authorization
OWASP Top 10
A01:2025 Broken Access Control
Published
Modified
NVD analysis
Analyzed
Record from
the NVD, synced

Fix and patched versions

Ask an AI about this CVE

Show the promptExplain CVE-2026-65975 for an engineer deciding whether to act. Use https://cve.bz/api/public/cves/CVE-2026-65975?via=ask-ai-copy and https://cve.bz/cve/CVE-2026-65975?via=ask-ai-copy as the source of truth: what is affected and which versions fix it, whether it is in CISA KEV, public exploits, and its EPSS (an internet-wide 30-day estimate of exploitation activity, not a forecast for my systems). If they give no fixed versions, use the CVE record https://cveawg.mitre.org/api/cve/CVE-2026-65975 or the vendor advisory, not third-party mirrors. Tell me how to check whether I am affected and how to verify a fix. Cite the sources and say where they are uncertain.

Opens a third-party assistant; its answer is its own, not cve.bz's. The prompt holds only this CVE's id and public links.

Affected

Versions

From the NVD's CPE matches.

ProductAffected
pydantic:pydantic_aifrom 1.88.0 before 1.107.1
pydantic:pydantic_aifrom 2.0.0 before 2.5.0

Red Hat

Red Hat rates this Moderate.

Red Hat's statement

This flaw in Pydantic AI allows remote clients to execute server tools with arbitrary arguments by bypassing message sanitization, potentially leading to unintended actions depending on the functionality of the exposed tools. This affects Red Hat Lightspeed Core when utilizing the vulnerable Pydantic AI framework.

Red Hat's mitigation

Configure Pydantic AI tools to require explicit approval for execution. This prevents remote clients from automatically executing server tools with forged arguments, as approval-gated tools are not affected by this vulnerability. Additionally, restrict network access to the Pydantic AI application to trusted clients only, if feasible in your environment.

ProductPackageStateAdvisory
Lightspeed Corelightspeed-core/lightspeed-stack-rhel9Fix deferred
Red Hat Enterprise Linux AI (RHEL AI) 3rhelai3/bootc-cuda-rhel9Not affected
Red Hat Enterprise Linux AI (RHEL AI) 3rhelai3/bootc-gaudi-rhel9Not affected
Red Hat Enterprise Linux AI (RHEL AI) 3rhelai3/bootc-rocm-rhel9Not affected
Red Hat Enterprise Linux AI (RHEL AI) 3rhelai3/disk-image-cuda-rhel9Not affected

Contains Red Hat Security Data © Red Hat, Inc., licensed under CC BY 4.0. Source: https://access.redhat.com/security/data. Modified: reformatted. Red Hat's page for CVE-2026-65975.

References

Check your stackJSON