CVE-2026-65975Network attack vector

Unauthenticated server tool execution via stale sanitization index

Published Jul 29, 2026 · Updated Jul 29, 2026

Incorrect authorization in affected Pydantic AI packages allows remote attackers to execute registered server tools with forged arguments. The sanitizer selects the dangling-call target from the pre-sanitization list; dropping an empty trailing message exposes an unchecked assistant tool call that the resume path dispatches. Exploitation requires an exposed AG-UI or Vercel AI adapter and a non-approval tool; the consequence is bounded by that tool, while approval-gated tools remain paused.

CVSS severity6.5
Medium
EPSS probability0.20%
Next 30 days · Sep 16, 2026
Known exploitationUnconfirmed
Based on sourced intelligence
Hinoki checkNot available
Coverage for this vulnerability

See if you're affected

Explore vulnerability checks for your environment with Hinoki.

Book a demo

Summary

What happened

Incorrect authorization in affected Pydantic AI packages allows remote attackers to execute registered server tools with forged arguments. The sanitizer selects the dangling-call target from the pre-sanitization list; dropping an empty trailing message exposes an unchecked assistant tool call that the resume path dispatches. Exploitation requires an exposed AG-UI or Vercel AI adapter and a non-approval tool; the consequence is bounded by that tool, while approval-gated tools remain paused.

The record

CVE
CVE-2026-65975
Published
Jul 29, 2026
Updated
Jul 29, 2026
Vendor
Pydantic
Product
Pydantic AI Slim
Classifications
CWE-863, T1190
Attack vector
network
Privileges
unauthenticated

Timeline

How it unfolded

  1. Jul 29, 2026CVE publishedPublication date reported by the CVE source.
  2. Jul 29, 2026Record updatedLatest update available in the CVE record.

Exploitability

Present is not the same as exploitable

Compare your product and version with the public record. A matching version still requires validation against your environment.

Is a vulnerable build present?

Compare these published version ranges with your installed build and any vendor patches.

  1. Affected versionversion=>= 1.88.0, < 1.107.1
  2. Affected versionversion=>= 2.0.0b1, < 2.5.0

What conditions does exploitation require?

Attack vectornetwork
Required privilegesunauthenticated

What is affected?

Pydantic · Pydantic AI Slimversion=>= 1.88.0, < 1.107.1; version=>= 2.0.0b1, < 2.5.0
Pydantic · Pydantic AIversion=>= 1.88.0, < 1.107.1; version=>= 2.0.0b1, < 2.5.0

Published CVSS scores

6.5GitHubCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:N

CVSS describes severity. EPSS estimates exploitation probability.

Attacks

What attackers are doing with it

Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.

Daily unique IPsNo honeypot observations are available for this CVE in the selected window.

No observations available

Sep 10, 2026Sep 16, 2026
Latest reporting daySep 16, 2026
Latest daily unique IPsUnavailable
Prior 30-day averageUnavailable
SourceShadowserver honeypots (KEV)
Vectornetwork
Privilegesunauthenticated
Known exploitationUnconfirmed
Public exploitUnconfirmed

Weakness, pattern, technique

CWE-863Incorrect Authorization
T1190Exploit Public-Facing Application

Public exploit references

No public exploit references are available in this record.

Labels summarize the accepted research assessment. They do not indicate a test against your environment.

Technologies

Your stack

See the directory against your own environment.

Your stack

Check the software in your environment

Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.

Book a demo