Skip to content
Noroxi
CVE-2026-65975· NVD / CVE Program· CNA GitHub_M

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.

MediumCVSS 6.5 · v3.1—No exploit No fix recorded
Published
Jul 29, 2026
Updated
Aug 4, 2026
EPSS
0.3% · 24th percentile
Follow this CVE

Sign in to follow · You’ll be notified if a followed record enters KEV, gets an exploit or is updated.

Report tools

JSON

Action score

26

Monitor

Low priority for now.

CVSS
26 / 40 · 6.5 / 10
CISA KEV
0 / 30 · Not listed
EPSS
0 / 30 · 0.3%

CISA SSVC decision

Exploitation
none
Automatable
yes
Technical impact
partial

Vulnrichment: CISA's decision-tree inputs.

CNA vs NVD score

NVD
—
CNA · GitHub_M
6.5
NVD has not scored this yet; the score shown is the CNA’s.

The score given by the assigning authority versus NVD’s independent score. A gap means the severity is contested.

Noroxi analysis

No Noroxi analysis for this record yet

We don't hand-write analysis for the hundreds of thousands of vulnerabilities in the database; that wouldn't be honest. For notable, high-impact vulnerabilities our team writes the mechanism, detection and remediation steps.

We use this product, ask for help

Affected systems

VendorProduct
pydanticpydantic ai

Affected versions

NVD version ranges (for catalog products). Add the product to your stack with a version and matching uses these.

  • pydantic pydantic ai1.88.0 and later · before 1.107.1
  • pydantic pydantic ai2.0.0 and later · before 2.5.0

Versions reported by the vendor

Affected version ranges reported by the assigning authority (GitHub_M). Independent of NVD's CPE analysis and usually ahead of it.

  • pydantic pydantic-ai

    • >= 1.88.0, < 1.107.1, >= 2.0.0b1, < 2.5.0affected

  • pydantic pydantic-ai-slim

    • >= 1.88.0, < 1.107.1, >= 2.0.0b1, < 2.5.0affected

Same product

pydantic: all records

Other highest-scoring records for the same primary product.

  • CVE-2026-25580Pydantic AI Affected by Server-Side Request Forgery (SSRF) in URL Download Handling
    34Monitor
  • CVE-2026-54249VercelAIAdapter trusts client-controlled `providerMetadata` to construct `UploadedFile` — S3/GCS confused deputy via provider metadata injection
    27Monitor
  • CVE-2026-48782pydantic-ai: SSRF blocklist bypass via IPv4-compatible, SIIT/IVI, and local NAT64 IPv6 addresses (incomplete fix of CVE-2026-46678)
    27Monitor
  • CVE-2026-46678Pydantic AI: SSRF cloud-metadata blocklist bypass via IPv4-mapped IPv6 (Incomplete fix of CVE-2026-25580)
    23Monitor
  • CVE-2026-25640Pydantic AI affected by Stored XSS via Path Traversal in Web UI CDN URL
    21Monitor

Remediation

Which version to upgrade to

Fix versions compiled from the vendor, package registries and Microsoft. Verify the vendor's note before upgrading.

No fix version is recorded for this entry. Check the references for vendor advisories.

Exploit status

No known public exploit

No public exploit has been observed yet. That doesn't mean you're safe, only that the bar is a little higher.

Research context

For pentesters and researchers: attack profile, score disagreement, timeline, patch commits, credits, variant and chain candidates, bug bounty scope. All derived from existing data; no exploit code.

Timeline

From publication to today: proof of concept, Metasploit module, CISA KEV and fix record. Dates are as reported by the sources.

No dated events beyond publication.

EPSS, last 120 days

FIRST EPSS daily score; only changes of 0.01 or more are recorded (step chart).

Patch and commit links

Commit, PR and diff links among the references. A starting point for patch-diffing and variant hunting; fixes, not exploits.

No commit or PR link among the references.

Credits

All researchers

Finders, reporters and analysts named in the CNA record. Click a name for that researcher’s other records.

No credits in the CNA record.

Variant candidates

Same product, same weakness class, within 18 months. If the patch missed the root cause, the sibling bug is here.

No nightly-computed relations.

Chain candidates

An authentication bypass and a privilege-requiring bug in the same product, published close together: combined they may become an unauthenticated path.

—

Bug bounty scope

No known public program.

Source: bounty-targets-data (public HackerOne, Bugcrowd, Intigriti, YesWeHack listings).

Technical details

Attack conditions

  • Anyone who can reach it over the internet can trigger it.
  • No account or password is required.
  • No user action is required.
  • No special conditions are required; it is repeatable.

If successful

Confidentiality
low · data can be read
Integrity
low · data or configuration can be modified
Availability
none
Attack vector
Network
Attack complexity
Low
Privileges required
None
User interaction
None
Scope
Unchanged
Confidentiality impact
Low
Integrity impact
Low
Availability impact
None

Weakness class (CWE)

CWE-863 · Incorrect Authorization

CVSS vector

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

nvd-secondary

Attack context

MITRE CAPEC attack patterns and ATT&CK techniques for this weakness class (CWE). A starting point for detection rules and threat hunting.

MITRE has no CAPEC/ATT&CK mapping for this CWE.

Change log

No changes recorded on tracked fields yet. Score, KEV, exploit maturity and fix status changes appear here.

References

Vendor advisories and official records. Exploit/PoC links are deliberately left out.

All records