Medium SSRF

CVE-2026-54249 — VercelAIAdapter trusts client-controlled `providerMetadata` to construct `UploadedFile` — S3/GCS confused deputy via provider metadata injection

Pydantic AI is a Python agent framework for building Generative AI applications. In versions 1.65.0 through 1.105.0, and 2.0.0b1 through 2.0.0b5, a client that submits message history to a Pydantic AI UI adapter (such as the Vercel AI adapter) can reference arbitrary files in the application's model-provider or cloud-storage account. While file URL parts are validated against a scheme allowlist, UploadedFile references — which point to a file by provider file ID or cloud-storage URI (e.g. s3://…, gs://…) — were forwarded without validation. Because the provider resolves an UploadedFile using the server-side identity (IAM role, service account, or provider API key) rather than the client's, an attacker can craft message history to make the server read objects from its own account or other tenants, given a referenceable identifier. Exploitation requires a valid file identifier, which is not always unguessable depending on how the application names objects. This issue has been fixed in versions 1.106.0 and 2.0.0b6.

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

EPSS 0.3% (30-day exploitation probability)+3
Technical severity (medium)+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

0.32%

ahead of 23% of scored CVEs · Oct 15, 2026

Affects

Pydantic

Pydantic Ai and 1 more

CVSS base

6.8

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

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 (ssrf), errors and authentication anomalies.

Affected scope

Vendor, product and versions as the sources word them.

Vendor	Product	Versions	Status	Source
Pydantic	Pydantic Ai	≥ 1.65.0 and < 1.105.0version 2.0.0-beta1version 2.0.0-beta2version 2.0.0-beta3version 2.0.0-beta4version 2.0.0-beta5	Vulnerable	NIST National Vulnerability Database
Pydantic	Pydantic Ai	version >= 1.65.0, < 1.106.0version >= 2.0.0b1, < 2.0.0b6	Vulnerable	CVE Program (cve.org) e CISA ADP
Pydantic	Pydantic-ai-slim	version >= 2.0.0b1, < 2.0.0b6version >= 1.65.0, < 1.106.0	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

High

Privileges required

None

User interaction

None

Scope

Changed

Confidentiality

High

Integrity

None

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
6.8	CVSS 3.1	Medium	2.2	4.0	security-advisories@github.com via NIST National Vulnerability Database
6.8	CVSS 3.1	Medium	—	—	GitHub_M via CVE Program (cve.org) e CISA ADP

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

Weakness MITRE

Weakness class according to MITRE’s CWE catalog.

CWE-918 · Server-Side Request Forgery (SSRF)

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).
Monitor outbound requests from the server to internal IPs and cloud metadata endpoints.

web/proxy/WAF logsnetwork IDS/IPSegress traffic

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 · 6.8
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-h7p7-w5gc-xj3w
Vendor Advisory, x_refsource_CONFIRM, NIST National Vulnerability Database

Elsewhere on this site

Pydantic
every CVE for this vendor

SSRF
same class

CWE-918
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 8d
Medium CVE-2026-107294 Pydantic AI: Unbounded memory use when downloading remote content via web_fetch or FileUrl 8d
Medium CVE-2026-107290 Pydantic AI: Event loop blocked by quadratic title extraction in `web_fetch` 8d
Medium CVE-2026-107292 Pydantic AI Web chat UI (`Agent.to_web()`, `clai web`): the local chat endpoint does not validate the `Host` header 8d
Medium CVE-2026-107291 Pydantic AI OpenTelemetry instrumentation: exception events on tool and agent run spans include content when `include_content=False` 8d
Medium CVE-2026-107293 Pydantic AI OpenTelemetry instrumentation: retry prompt content is not redacted when `include_content=False` 8d

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 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-2026-54249 is "VercelAIAdapter trusts client-controlled `providerMetadata` to construct `UploadedFile` — S3/GCS confused deputy via provider metadata injection", 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 6.8 describes technical severity. EPSS 0.32% estimates the probability of exploitation in 30 days; neither replaces your asset context. 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.