Medium Access control

CVE-2026-65975 — Pydantic AI AG-UI Adapter: A dangling client-submitted tool call can execute when a trailing message is dropped during `sanitize_messages`

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.

Published Jul 29, 2026 · Updated Oct 15, 2026 · Sources: NIST National Vulnerability Database, CVE Program (cve.org) e CISA ADP · CNA: GitHub_M

Low

Who exploits it and how urgent it is

A 0–100 score combining confirmed exploitation, ransomware and APT use, public exploits, EPSS and severity.

No exploitation signal in the sources consulted so far.

How the score was calculated

Technical severity (medium)+3
Automatable exploitation (SSVC)+3

The score orders the patch queue; it does not replace your asset context (internet exposure, criticality, compensating controls).

Triage

Is it exploited, how likely is exploitation, what does it touch, and how severe do the sources call it.

Exploitation

Not confirmed

Not in CISA KEV — an absence of record, not proof it is unexploited.

EPSS FIRST

—

No EPSS score.

Affects

Pydantic

Pydantic Ai and 1 more

CVSS base

6.5

Medium · 2 source(s)

CISA SSVC assessment CISA

Three decision points CISA publishes for the CVEs it assesses (SSVC 2.0.3). A stakeholder decision, not a severity score.

Exploitation

None

none · proof-of-concept · active

Automatable

Yes

can an attacker script the kill-chain steps

Technical impact

Partial

partial · total control of the vulnerable component

Remediation

Fixes and mitigations documented by the sources — linked to the original advisory.

No fix documented by the sources we poll. That does not mean none exists: check the vendor advisory.

First 24 hours

Ordered from the record’s own fields — exposure first, because you cannot patch what you have not found. A rule-generated starting point.

Identify exposed assets running the affected vendor/product/version combinations (Pydantic Pydantic Ai, Pydantic Pydantic-ai-slim).
The attack is network-based and needs no privileges: restrict exposure (ACLs, VPN, WAF) until patched.
No fix documented in the sources: reduce exposure and monitor the vendor advisory.
Search available logs for exploit probes matching the vulnerability class (access control), errors and authentication anomalies.

Affected scope

Vendor, product and versions as the sources word them.

Vendor	Product	Versions	Status	Source
Pydantic	Pydantic Ai	≥ 1.88.0 and < 1.107.1≥ 2.0.0 and < 2.5.0	Vulnerable	NIST National Vulnerability Database
Pydantic	Pydantic Ai	version >= 1.88.0, < 1.107.1version >= 2.0.0b1, < 2.5.0	Vulnerable	CVE Program (cve.org) e CISA ADP
Pydantic	Pydantic-ai-slim	version >= 1.88.0, < 1.107.1version >= 2.0.0b1, < 2.5.0	Vulnerable	CVE Program (cve.org) e CISA ADP

Attack characteristics

The CVSS vector, decoded. It describes the attack, not your exposure to it.

Attack vector

Network

Attack complexity

Low

Privileges required

None

User interaction

None

Scope

Unchanged

Confidentiality

Low

Integrity

Low

Availability

None

Every base score collected

Sources score independently and may disagree; each row says who scored it and under which version.

Score	Version	Severity	Expl.	Impact	Scored by
6.5	CVSS 3.1	Medium	3.9	2.5	security-advisories@github.com via NIST National Vulnerability Database
6.5	CVSS 3.1	Medium	—	—	GitHub_M via CVE Program (cve.org) e CISA ADP

CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:N (score shown at the top: security-advisories@github.com)

Weakness MITRE

Weakness class according to MITRE’s CWE catalog.

CWE-863 · Incorrect Authorization

Other CVEs with this weakness →

Detection

Read off the CVSS vector and the weakness class. Starting points, not tested rules.

Prioritize edge telemetry for the network-reachable component (proxy, WAF, IDS/IPS).
Audit administrative actions and access to resources outside each user’s normal pattern.

web/proxy/WAF logsnetwork IDS/IPSauthentication logsapplication logs

Timeline

What happened to this CVE, newest first.

2026
Affected products added · pydantic/pydantic-ai, pydantic/pydantic-ai-slim
Oct 15, 2026 · CVE Program (cve.org) e CISA ADP
SSVC assessment updated
Oct 15, 2026 · CVE Program (cve.org) e CISA ADP
Record published
Oct 15, 2026
CVSS changed · 6.5
Oct 15, 2026 · NIST National Vulnerability Database
Source status changed · → Analyzed
Oct 15, 2026 · NIST National Vulnerability Database
Record created in this database
Oct 15, 2026 · NIST National Vulnerability Database
CVE published
Jul 29, 2026 · GitHub_M

Source activity

Repeated readings are counted rather than listed.

1× Official description updated · Oct 15, 2026 – Oct 15, 2026

References

1 on the record

github.com/pydantic/pydantic-ai/security/advisories/GHSA-jpr8-2v3g-wgf9
Vendor Advisory, x_refsource_CONFIRM, NIST National Vulnerability Database

Elsewhere on this site

Pydantic
every CVE for this vendor

Access control
same class

CWE-863
other pages naming this weakness

Related CVEs (same products)

High CVE-2026-107295 `pydantic-ai-slim` web UI `/api/chat` accepts browser-simple cross-origin requests that can trigger agent tool execution 7d
Medium CVE-2026-107294 Pydantic AI: Unbounded memory use when downloading remote content via web_fetch or FileUrl 7d
Medium CVE-2026-107290 Pydantic AI: Event loop blocked by quadratic title extraction in `web_fetch` 7d
Medium CVE-2026-107292 Pydantic AI Web chat UI (`Agent.to_web()`, `clai web`): the local chat endpoint does not validate the `Host` header 7d
Medium CVE-2026-107291 Pydantic AI OpenTelemetry instrumentation: exception events on tool and agent run spans include content when `include_content=False` 7d
Medium CVE-2026-107293 Pydantic AI OpenTelemetry instrumentation: retry prompt content is not redacted when `include_content=False` 7d

Not in any source we poll

Listed rather than left blank: an empty field and an unmeasured one look identical on screen, and only one is a reason to look elsewhere.

No FIRST EPSS score.
No fixed version, patch or mitigation documented.
No confirmed IOCs, IP addresses, domains, file hashes, or malware artifacts supplied.
No organization-specific asset inventory, compensating-control status, or patch deployment evidence supplied.
No exploit packet captures, log samples, or incident case IDs supplied.

Answered from this record

Text assembled only from the fields above — no additional claims.

What should defenders know first?

CVE-2026-65975 is "Pydantic AI AG-UI Adapter: A dangling client-submitted tool call can execute when a trailing message is dropped during `sanitize_messages`", rated Medium. It affects Pydantic Ai (Pydantic); versions are in the scope table. It is not in CISA KEV, which does not rule out exploitation. CVSS 6.5 describes technical severity. First verify whether exposed or business-critical assets run the affected versions, apply vendor fixes or mitigations, and preserve logs for review.

Comments

Moderated technical discussion. Read the community guidelines.

No comments yet.