CVE-2026-54249 (GCVE-0-2026-54249)
Vulnerability from cvelistv5 – Published: 2026-07-29 20:28 – Updated: 2026-07-30 13:08
VLAI
EPSS
VEX
Title
VercelAIAdapter trusts client-controlled `providerMetadata` to construct `UploadedFile` — S3/GCS confused deputy via provider metadata injection
Summary
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.
Severity
6.8 (Medium)
SSVC
Exploitation: none
Automatable: no
Technical Impact: partial
CISA Coordinator (v2.0.3)
CWE
- CWE-918 - Server-Side Request Forgery (SSRF)
Assigner
References
1 reference
| URL | Tags |
|---|---|
| https://github.com/pydantic/pydantic-ai/security/… | x_refsource_CONFIRM |
Impacted products
2 products
| Vendor | Product | Version | |
|---|---|---|---|
| pydantic | pydantic-ai |
Affected:
>= 1.65.0, < 1.106.0
Affected: >= 2.0.0b1, < 2.0.0b6 |
|
| pydantic | pydantic-ai-slim |
Affected:
>= 2.0.0b1, < 2.0.0b6
Affected: >= 1.65.0, < 1.106.0 |
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-54249",
"options": [
{
"Exploitation": "none"
},
{
"Automatable": "no"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-07-30T13:08:03.344276Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-07-30T13:08:12.954Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "pydantic-ai",
"vendor": "pydantic",
"versions": [
{
"status": "affected",
"version": "\u003e= 1.65.0, \u003c 1.106.0"
},
{
"status": "affected",
"version": "\u003e= 2.0.0b1, \u003c 2.0.0b6"
}
]
},
{
"product": "pydantic-ai-slim",
"vendor": "pydantic",
"versions": [
{
"status": "affected",
"version": "\u003e= 2.0.0b1, \u003c 2.0.0b6"
},
{
"status": "affected",
"version": "\u003e= 1.65.0, \u003c 1.106.0"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "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\u0027s model-provider or cloud-storage account. While file URL parts are validated against a scheme allowlist, UploadedFile references \u2014 which point to a file by provider file ID or cloud-storage URI (e.g. s3://\u2026, gs://\u2026) \u2014 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\u0027s, 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."
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "HIGH",
"attackVector": "NETWORK",
"availabilityImpact": "NONE",
"baseScore": 6.8,
"baseSeverity": "MEDIUM",
"confidentialityImpact": "HIGH",
"integrityImpact": "NONE",
"privilegesRequired": "NONE",
"scope": "CHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:C/C:H/I:N/A:N",
"version": "3.1"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-918",
"description": "CWE-918: Server-Side Request Forgery (SSRF)",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-07-29T20:28:07.154Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/pydantic/pydantic-ai/security/advisories/GHSA-h7p7-w5gc-xj3w",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/pydantic/pydantic-ai/security/advisories/GHSA-h7p7-w5gc-xj3w"
}
],
"source": {
"advisory": "GHSA-h7p7-w5gc-xj3w",
"discovery": "UNKNOWN"
},
"title": "VercelAIAdapter trusts client-controlled `providerMetadata` to construct `UploadedFile` \u2014 S3/GCS confused deputy via provider metadata injection"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2026-54249",
"datePublished": "2026-07-29T20:28:07.154Z",
"dateReserved": "2026-06-12T16:25:43.085Z",
"dateUpdated": "2026-07-30T13:08:12.954Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2",
"vulnerability-lookup:meta": {
"epss": {
"cve": "CVE-2026-54249",
"date": "2026-08-04",
"epss": "0.00197",
"percentile": "0.0966"
},
"nvd": "{\"cve\":{\"id\":\"CVE-2026-54249\",\"sourceIdentifier\":\"security-advisories@github.com\",\"published\":\"2026-07-29T21:17:47.323\",\"lastModified\":\"2026-08-04T13:22:03.630\",\"vulnStatus\":\"Analyzed\",\"cveTags\":[],\"descriptions\":[{\"lang\":\"en\",\"value\":\"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\u0027s model-provider or cloud-storage account. While file URL parts are validated against a scheme allowlist, UploadedFile references \u2014 which point to a file by provider file ID or cloud-storage URI (e.g. s3://\u2026, gs://\u2026) \u2014 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\u0027s, 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.\"}],\"affected\":[{\"source\":\"security-advisories@github.com\",\"affectedData\":[{\"vendor\":\"pydantic\",\"product\":\"pydantic-ai\",\"versions\":[{\"version\":\"\u003e= 1.65.0, \u003c 1.106.0\",\"status\":\"affected\"},{\"version\":\"\u003e= 2.0.0b1, \u003c 2.0.0b6\",\"status\":\"affected\"}]},{\"vendor\":\"pydantic\",\"product\":\"pydantic-ai-slim\",\"versions\":[{\"version\":\"\u003e= 2.0.0b1, \u003c 2.0.0b6\",\"status\":\"affected\"},{\"version\":\"\u003e= 1.65.0, \u003c 1.106.0\",\"status\":\"affected\"}]}]}],\"metrics\":{\"cvssMetricV31\":[{\"source\":\"security-advisories@github.com\",\"type\":\"Secondary\",\"cvssData\":{\"version\":\"3.1\",\"vectorString\":\"CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:C/C:H/I:N/A:N\",\"baseScore\":6.8,\"baseSeverity\":\"MEDIUM\",\"attackVector\":\"NETWORK\",\"attackComplexity\":\"HIGH\",\"privilegesRequired\":\"NONE\",\"userInteraction\":\"NONE\",\"scope\":\"CHANGED\",\"confidentialityImpact\":\"HIGH\",\"integrityImpact\":\"NONE\",\"availabilityImpact\":\"NONE\"},\"exploitabilityScore\":2.2,\"impactScore\":4.0}],\"ssvcV203\":[{\"source\":\"134c704f-9b21-4f2e-91b3-4a467353bcc0\",\"ssvcData\":{\"timestamp\":\"2026-07-30T13:08:03.344276Z\",\"id\":\"CVE-2026-54249\",\"options\":[{\"exploitation\":\"none\"},{\"automatable\":\"no\"},{\"technicalImpact\":\"partial\"}],\"role\":\"CISA Coordinator\",\"version\":\"2.0.3\"}}]},\"weaknesses\":[{\"source\":\"security-advisories@github.com\",\"type\":\"Secondary\",\"description\":[{\"lang\":\"en\",\"value\":\"CWE-918\"}]}],\"configurations\":[{\"nodes\":[{\"operator\":\"OR\",\"negate\":false,\"cpeMatch\":[{\"vulnerable\":true,\"criteria\":\"cpe:2.3:a:pydantic:pydantic_ai:*:*:*:*:*:python:*:*\",\"versionStartIncluding\":\"1.65.0\",\"versionEndExcluding\":\"1.105.0\",\"matchCriteriaId\":\"5D7A39AC-6B48-468C-8FE1-4E5FEEA9B693\"},{\"vulnerable\":true,\"criteria\":\"cpe:2.3:a:pydantic:pydantic_ai:2.0.0:beta1:*:*:*:python:*:*\",\"matchCriteriaId\":\"7F40BA40-4529-43DA-A120-BD18300297A0\"},{\"vulnerable\":true,\"criteria\":\"cpe:2.3:a:pydantic:pydantic_ai:2.0.0:beta2:*:*:*:python:*:*\",\"matchCriteriaId\":\"9CA57AD6-2B0E-4DCB-A2B7-902A1E65CA1C\"},{\"vulnerable\":true,\"criteria\":\"cpe:2.3:a:pydantic:pydantic_ai:2.0.0:beta3:*:*:*:python:*:*\",\"matchCriteriaId\":\"C334714F-3BEC-460A-8D91-C520714F697C\"},{\"vulnerable\":true,\"criteria\":\"cpe:2.3:a:pydantic:pydantic_ai:2.0.0:beta4:*:*:*:python:*:*\",\"matchCriteriaId\":\"B5ECE52B-4D6F-45F8-8130-325E92442852\"},{\"vulnerable\":true,\"criteria\":\"cpe:2.3:a:pydantic:pydantic_ai:2.0.0:beta5:*:*:*:python:*:*\",\"matchCriteriaId\":\"2FA7C8EF-F233-4DC7-8E03-A29245CD97BF\"}]}]}],\"references\":[{\"url\":\"https://github.com/pydantic/pydantic-ai/security/advisories/GHSA-h7p7-w5gc-xj3w\",\"source\":\"security-advisories@github.com\",\"tags\":[\"Vendor Advisory\"]}]}}",
"redhat_vex": {
"aggregate_severity": "Moderate",
"current_release_date": "2026-07-30T14:46:34+00:00",
"cve": "CVE-2026-54249",
"id": "CVE-2026-54249",
"initial_release_date": "2026-07-29T20:28:07.154000+00:00",
"product_status:known_not_affected": "5",
"source": "Red Hat CSAF VEX",
"status": "final",
"title": "pydantic-ai: Pydantic AI: Information disclosure through unvalidated file references.",
"url": "https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-54249.json",
"version": "3"
},
"vulnrichment": {
"containers": "{\"cna\": {\"title\": \"VercelAIAdapter trusts client-controlled `providerMetadata` to construct `UploadedFile` \\u2014 S3/GCS confused deputy via provider metadata injection\", \"source\": {\"advisory\": \"GHSA-h7p7-w5gc-xj3w\", \"discovery\": \"UNKNOWN\"}, \"metrics\": [{\"cvssV3_1\": {\"scope\": \"CHANGED\", \"version\": \"3.1\", \"baseScore\": 6.8, \"attackVector\": \"NETWORK\", \"baseSeverity\": \"MEDIUM\", \"vectorString\": \"CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:C/C:H/I:N/A:N\", \"integrityImpact\": \"NONE\", \"userInteraction\": \"NONE\", \"attackComplexity\": \"HIGH\", \"availabilityImpact\": \"NONE\", \"privilegesRequired\": \"NONE\", \"confidentialityImpact\": \"HIGH\"}}], \"affected\": [{\"vendor\": \"pydantic\", \"product\": \"pydantic-ai\", \"versions\": [{\"status\": \"affected\", \"version\": \"\u003e= 1.65.0, \u003c 1.106.0\"}, {\"status\": \"affected\", \"version\": \"\u003e= 2.0.0b1, \u003c 2.0.0b6\"}]}, {\"vendor\": \"pydantic\", \"product\": \"pydantic-ai-slim\", \"versions\": [{\"status\": \"affected\", \"version\": \"\u003e= 2.0.0b1, \u003c 2.0.0b6\"}, {\"status\": \"affected\", \"version\": \"\u003e= 1.65.0, \u003c 1.106.0\"}]}], \"references\": [{\"url\": \"https://github.com/pydantic/pydantic-ai/security/advisories/GHSA-h7p7-w5gc-xj3w\", \"name\": \"https://github.com/pydantic/pydantic-ai/security/advisories/GHSA-h7p7-w5gc-xj3w\", \"tags\": [\"x_refsource_CONFIRM\"]}], \"descriptions\": [{\"lang\": \"en\", \"value\": \"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\u0027s model-provider or cloud-storage account. While file URL parts are validated against a scheme allowlist, UploadedFile references \\u2014 which point to a file by provider file ID or cloud-storage URI (e.g. s3://\\u2026, gs://\\u2026) \\u2014 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\u0027s, 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.\"}], \"problemTypes\": [{\"descriptions\": [{\"lang\": \"en\", \"type\": \"CWE\", \"cweId\": \"CWE-918\", \"description\": \"CWE-918: Server-Side Request Forgery (SSRF)\"}]}], \"providerMetadata\": {\"orgId\": \"a0819718-46f1-4df5-94e2-005712e83aaa\", \"shortName\": \"GitHub_M\", \"dateUpdated\": \"2026-07-29T20:28:07.154Z\"}}, \"adp\": [{\"title\": \"CISA ADP Vulnrichment\", \"metrics\": [{\"other\": {\"type\": \"ssvc\", \"content\": {\"id\": \"CVE-2026-54249\", \"role\": \"CISA Coordinator\", \"options\": [{\"Exploitation\": \"none\"}, {\"Automatable\": \"no\"}, {\"Technical Impact\": \"partial\"}], \"version\": \"2.0.3\", \"timestamp\": \"2026-07-30T13:08:03.344276Z\"}}}], \"providerMetadata\": {\"shortName\": \"CISA-ADP\", \"orgId\": \"134c704f-9b21-4f2e-91b3-4a467353bcc0\", \"dateUpdated\": \"2026-07-30T13:08:08.990Z\"}}]}",
"cveMetadata": "{\"cveId\": \"CVE-2026-54249\", \"state\": \"PUBLISHED\", \"dateUpdated\": \"2026-07-29T20:28:07.154Z\", \"dateReserved\": \"2026-06-12T16:25:43.085Z\", \"assignerOrgId\": \"a0819718-46f1-4df5-94e2-005712e83aaa\", \"datePublished\": \"2026-07-29T20:28:07.154Z\", \"assignerShortName\": \"GitHub_M\"}",
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
}
}
Loading…
Loading…
Experimental. This forecast is provided for visualization only and may change without notice. Do not use it for operational decisions.
Forecast uses a logistic model when the trend is rising, or an exponential decay model when the trend is falling. Fitted via linearized least squares.
Sightings
| Author | Source | Type | Date | Other |
|---|
Nomenclature
- Seen: The vulnerability was mentioned, discussed, or observed by the user.
- Confirmed: The vulnerability has been validated from an analyst's perspective.
- Published Proof of Concept: A public proof of concept is available for this vulnerability.
- Exploited: The vulnerability was observed as exploited by the user who reported the sighting.
- Patched: The vulnerability was observed as successfully patched by the user who reported the sighting.
- Not exploited: The vulnerability was not observed as exploited by the user who reported the sighting.
- Not confirmed: The user expressed doubt about the validity of the vulnerability.
- Not patched: The vulnerability was not observed as successfully patched by the user who reported the sighting.
Loading…
The MITRE ATT&CK techniques below are AI-generated suggestions, inferred from the description of the
vulnerability by the CIRCL/vulnerability-attack-technique-classification-roberta-base
model, served locally by ML-Gateway.
They have not been verified by an analyst and are provided for guidance only.
Loading…
Loading…