Search
Find a vulnerability
Search criteria
6 vulnerabilities by Unstructured-IO
CVE-2026-104250 (GCVE-0-2026-104250)
Vulnerability from nvd – Published: 2026-10-13 16:29 – Updated: 2026-10-14 15:32
VLAI
EPSS
VEX
Title
unstructured: Stored XSS via unescaped HTML generation
Summary
The unstructured library provides open-source components for ingesting and pre-processing images and text documents, such as PDFs, HTML, Word docs, and many more. Prior to 0.24.1, partition_html(html_parser_version="v2") and the VLM partitioner can preserve untrusted document tags, attributes, text, and link targets in metadata.text_as_html, while elements_to_html() emits the result as an HTML document. The to_html() path in unstructured/documents/ontology.py does not escape output or reject unsafe URL schemes, allowing event-handler attributes, attribute breakout markup, and javascript: links to survive parsing. When the generated HTML or text_as_html is rendered in a browser, attacker-controlled script can execute in the viewer's origin, including in document-ingestion workflows where a privileged reviewer opens submitted content. This issue is fixed in version 0.24.1.
Severity
6.1 (Medium)
SSVC
Exploitation: poc
Automatable: no
Technical Impact: partial
CISA Coordinator · CISA-ADP (v2.0.3)
Decision recorded 2026-10-14 15:32 UTC
CWE
Assigner
References
4 references
| URL | Tags |
|---|---|
| https://github.com/Unstructured-IO/unstructured/s… | x_refsource_CONFIRM |
| https://github.com/Unstructured-IO/unstructured/p… | x_refsource_MISC |
| https://github.com/Unstructured-IO/unstructured/c… | x_refsource_MISC |
| https://github.com/Unstructured-IO/unstructured/r… | x_refsource_MISC |
Impacted products
1 product
| Vendor | Product | Version | |
|---|---|---|---|
| Unstructured-IO | unstructured |
Affected:
< 0.24.1
|
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-104250",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "no"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-10-14T15:32:11.460266Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-10-14T15:32:42.130Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"references": [
{
"tags": [
"exploit"
],
"url": "https://github.com/Unstructured-IO/unstructured/security/advisories/GHSA-v5mq-3xhg-98m9"
}
],
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "unstructured",
"vendor": "Unstructured-IO",
"versions": [
{
"status": "affected",
"version": "\u003c 0.24.1"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "The unstructured library provides open-source components for ingesting and pre-processing images and text documents, such as PDFs, HTML, Word docs, and many more. Prior to 0.24.1, partition_html(html_parser_version=\"v2\") and the VLM partitioner can preserve untrusted document tags, attributes, text, and link targets in metadata.text_as_html, while elements_to_html() emits the result as an HTML document. The to_html() path in unstructured/documents/ontology.py does not escape output or reject unsafe URL schemes, allowing event-handler attributes, attribute breakout markup, and javascript: links to survive parsing. When the generated HTML or text_as_html is rendered in a browser, attacker-controlled script can execute in the viewer\u0027s origin, including in document-ingestion workflows where a privileged reviewer opens submitted content. This issue is fixed in version 0.24.1."
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "NONE",
"baseScore": 6.1,
"baseSeverity": "MEDIUM",
"confidentialityImpact": "LOW",
"integrityImpact": "LOW",
"privilegesRequired": "NONE",
"scope": "CHANGED",
"userInteraction": "REQUIRED",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:L/I:L/A:N",
"version": "3.1"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-79",
"description": "CWE-79: Improper Neutralization of Input During Web Page Generation (\u0027Cross-site Scripting\u0027)",
"lang": "en",
"type": "CWE"
}
]
},
{
"descriptions": [
{
"cweId": "CWE-116",
"description": "CWE-116: Improper Encoding or Escaping of Output",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-10-13T16:29:28.813Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/Unstructured-IO/unstructured/security/advisories/GHSA-v5mq-3xhg-98m9",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/Unstructured-IO/unstructured/security/advisories/GHSA-v5mq-3xhg-98m9"
},
{
"name": "https://github.com/Unstructured-IO/unstructured/pull/4394",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/Unstructured-IO/unstructured/pull/4394"
},
{
"name": "https://github.com/Unstructured-IO/unstructured/commit/cda16b3f2170019be9c6ea5635946fb3eaa2d66f",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/Unstructured-IO/unstructured/commit/cda16b3f2170019be9c6ea5635946fb3eaa2d66f"
},
{
"name": "https://github.com/Unstructured-IO/unstructured/releases/tag/0.24.1",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/Unstructured-IO/unstructured/releases/tag/0.24.1"
}
],
"source": {
"advisory": "GHSA-v5mq-3xhg-98m9",
"discovery": "UNKNOWN"
},
"title": "unstructured: Stored XSS via unescaped HTML generation"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2026-104250",
"datePublished": "2026-10-13T16:29:28.813Z",
"dateReserved": "2026-10-01T19:04:39.706Z",
"dateUpdated": "2026-10-14T15:32:42.130Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2026-71428 (GCVE-0-2026-71428)
Vulnerability from nvd – Published: 2026-08-20 16:43 – Updated: 2026-08-25 15:05
VLAI
EPSS
VEX
Title
unstructured: Server-Side Request Forgery in the URL-based partitioning
Summary
The unstructured library provides open-source components for ingesting and pre-processing images and text documents, such as PDFs, HTML, Word docs, and many more. From 0.4.7 until 0.24.0, the url argument of partition, partition_html, and partition_md is fetched without host validation in unstructured/partition/auto.py, unstructured/partition/html/partition.py, and unstructured/partition/md.py. An attacker who controls that URL can make a server-side ingestion service request loopback addresses, internal HTTP services, or cloud metadata endpoints through direct targets, redirects, or DNS rebinding. The response body is returned as Element text, allowing internal response disclosure, and side-effecting GET endpoints may also be triggered. This issue is fixed in version 0.24.0.
Severity
9.3 (Critical)
SSVC
Exploitation: poc
Automatable: yes
Technical Impact: partial
CISA Coordinator · CISA-ADP (v2.0.3)
Decision recorded 2026-08-25 15:05 UTC
CWE
Assigner
References
4 references
| URL | Tags |
|---|---|
| https://github.com/Unstructured-IO/unstructured/s… | x_refsource_CONFIRM |
| https://github.com/Unstructured-IO/unstructured/p… | x_refsource_MISC |
| https://github.com/Unstructured-IO/unstructured/c… | x_refsource_MISC |
| https://github.com/Unstructured-IO/unstructured/r… | x_refsource_MISC |
Impacted products
1 product
| Vendor | Product | Version | |
|---|---|---|---|
| Unstructured-IO | unstructured |
Affected:
>= 0.4.7, < 0.24.0
|
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-71428",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "yes"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-08-25T15:05:06.666433Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-08-25T15:05:17.185Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "unstructured",
"vendor": "Unstructured-IO",
"versions": [
{
"status": "affected",
"version": "\u003e= 0.4.7, \u003c 0.24.0"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "The unstructured library provides open-source components for ingesting and pre-processing images and text documents, such as PDFs, HTML, Word docs, and many more. From 0.4.7 until 0.24.0, the url argument of partition, partition_html, and partition_md is fetched without host validation in unstructured/partition/auto.py, unstructured/partition/html/partition.py, and unstructured/partition/md.py. An attacker who controls that URL can make a server-side ingestion service request loopback addresses, internal HTTP services, or cloud metadata endpoints through direct targets, redirects, or DNS rebinding. The response body is returned as Element text, allowing internal response disclosure, and side-effecting GET endpoints may also be triggered. This issue is fixed in version 0.24.0."
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "NONE",
"baseScore": 9.3,
"baseSeverity": "CRITICAL",
"confidentialityImpact": "HIGH",
"integrityImpact": "LOW",
"privilegesRequired": "NONE",
"scope": "CHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:L/A:N",
"version": "3.1"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-601",
"description": "CWE-601: URL Redirection to Untrusted Site (\u0027Open Redirect\u0027)",
"lang": "en",
"type": "CWE"
}
]
},
{
"descriptions": [
{
"cweId": "CWE-918",
"description": "CWE-918: Server-Side Request Forgery (SSRF)",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-08-20T16:43:01.306Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/Unstructured-IO/unstructured/security/advisories/GHSA-4mvj-m6j5-pmf7",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/Unstructured-IO/unstructured/security/advisories/GHSA-4mvj-m6j5-pmf7"
},
{
"name": "https://github.com/Unstructured-IO/unstructured/pull/4388",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/Unstructured-IO/unstructured/pull/4388"
},
{
"name": "https://github.com/Unstructured-IO/unstructured/commit/445c95735c4045057f51f399bc04c657751923bd",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/Unstructured-IO/unstructured/commit/445c95735c4045057f51f399bc04c657751923bd"
},
{
"name": "https://github.com/Unstructured-IO/unstructured/releases/tag/0.24.0",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/Unstructured-IO/unstructured/releases/tag/0.24.0"
}
],
"source": {
"advisory": "GHSA-4mvj-m6j5-pmf7",
"discovery": "UNKNOWN"
},
"title": "unstructured: Server-Side Request Forgery in the URL-based partitioning"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2026-71428",
"datePublished": "2026-08-20T16:43:01.306Z",
"dateReserved": "2026-08-06T16:28:51.182Z",
"dateUpdated": "2026-08-25T15:05:17.185Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2025-64712 (GCVE-0-2025-64712)
Vulnerability from nvd – Published: 2026-02-04 17:34 – Updated: 2026-02-04 19:24
VLAI
EPSS
VEX
Title
Unstructured has Path Traversal via Malicious MSG Attachment that Allows Arbitrary File Write
Summary
The unstructured library provides open-source components for ingesting and pre-processing images and text documents, such as PDFs, HTML, Word docs, and many more. Prior to version 0.18.18, a path traversal vulnerability in the partition_msg function allows an attacker to write or overwrite arbitrary files on the filesystem when processing malicious MSG files with attachments. This issue has been patched in version 0.18.18.
Severity
9.8 (Critical)
SSVC
Exploitation: none
Automatable: yes
Technical Impact: total
CISA Coordinator · CISA-ADP (v2.0.3)
Decision recorded 2026-02-04 19:24 UTC
CWE
Assigner
References
2 references
| URL | Tags |
|---|---|
| https://github.com/Unstructured-IO/unstructured/s… | x_refsource_CONFIRM |
| https://github.com/Unstructured-IO/unstructured/c… | x_refsource_MISC |
Impacted products
1 product
| Vendor | Product | Version | |
|---|---|---|---|
| Unstructured-IO | unstructured |
Affected:
< 0.18.18
|
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2025-64712",
"options": [
{
"Exploitation": "none"
},
{
"Automatable": "yes"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-02-04T19:24:03.397110Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-02-04T19:24:12.411Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "unstructured",
"vendor": "Unstructured-IO",
"versions": [
{
"status": "affected",
"version": "\u003c 0.18.18"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "The unstructured library provides open-source components for ingesting and pre-processing images and text documents, such as PDFs, HTML, Word docs, and many more. Prior to version 0.18.18, a path traversal vulnerability in the partition_msg function allows an attacker to write or overwrite arbitrary files on the filesystem when processing malicious MSG files with attachments. This issue has been patched in version 0.18.18."
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "HIGH",
"baseScore": 9.8,
"baseSeverity": "CRITICAL",
"confidentialityImpact": "HIGH",
"integrityImpact": "HIGH",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H",
"version": "3.1"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-22",
"description": "CWE-22: Improper Limitation of a Pathname to a Restricted Directory (\u0027Path Traversal\u0027)",
"lang": "en",
"type": "CWE"
}
]
},
{
"descriptions": [
{
"cweId": "CWE-73",
"description": "CWE-73: External Control of File Name or Path",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-02-04T17:34:51.426Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/Unstructured-IO/unstructured/security/advisories/GHSA-gm8q-m8mv-jj5m",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/Unstructured-IO/unstructured/security/advisories/GHSA-gm8q-m8mv-jj5m"
},
{
"name": "https://github.com/Unstructured-IO/unstructured/commit/b01d35b2373fd087d2e15162b9c021663c97155d",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/Unstructured-IO/unstructured/commit/b01d35b2373fd087d2e15162b9c021663c97155d"
}
],
"source": {
"advisory": "GHSA-gm8q-m8mv-jj5m",
"discovery": "UNKNOWN"
},
"title": "Unstructured has Path Traversal via Malicious MSG Attachment that Allows Arbitrary File Write"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2025-64712",
"datePublished": "2026-02-04T17:34:51.426Z",
"dateReserved": "2025-11-10T14:07:42.921Z",
"dateUpdated": "2026-02-04T19:24:12.411Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2026-104250 (GCVE-0-2026-104250)
Vulnerability from cvelistv5 – Published: 2026-10-13 16:29 – Updated: 2026-10-14 15:32
VLAI
EPSS
VEX
Title
unstructured: Stored XSS via unescaped HTML generation
Summary
The unstructured library provides open-source components for ingesting and pre-processing images and text documents, such as PDFs, HTML, Word docs, and many more. Prior to 0.24.1, partition_html(html_parser_version="v2") and the VLM partitioner can preserve untrusted document tags, attributes, text, and link targets in metadata.text_as_html, while elements_to_html() emits the result as an HTML document. The to_html() path in unstructured/documents/ontology.py does not escape output or reject unsafe URL schemes, allowing event-handler attributes, attribute breakout markup, and javascript: links to survive parsing. When the generated HTML or text_as_html is rendered in a browser, attacker-controlled script can execute in the viewer's origin, including in document-ingestion workflows where a privileged reviewer opens submitted content. This issue is fixed in version 0.24.1.
Severity
6.1 (Medium)
SSVC
Exploitation: poc
Automatable: no
Technical Impact: partial
CISA Coordinator · CISA-ADP (v2.0.3)
Decision recorded 2026-10-14 15:32 UTC
CWE
Assigner
References
4 references
| URL | Tags |
|---|---|
| https://github.com/Unstructured-IO/unstructured/s… | x_refsource_CONFIRM |
| https://github.com/Unstructured-IO/unstructured/p… | x_refsource_MISC |
| https://github.com/Unstructured-IO/unstructured/c… | x_refsource_MISC |
| https://github.com/Unstructured-IO/unstructured/r… | x_refsource_MISC |
Impacted products
1 product
| Vendor | Product | Version | |
|---|---|---|---|
| Unstructured-IO | unstructured |
Affected:
< 0.24.1
|
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-104250",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "no"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-10-14T15:32:11.460266Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-10-14T15:32:42.130Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"references": [
{
"tags": [
"exploit"
],
"url": "https://github.com/Unstructured-IO/unstructured/security/advisories/GHSA-v5mq-3xhg-98m9"
}
],
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "unstructured",
"vendor": "Unstructured-IO",
"versions": [
{
"status": "affected",
"version": "\u003c 0.24.1"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "The unstructured library provides open-source components for ingesting and pre-processing images and text documents, such as PDFs, HTML, Word docs, and many more. Prior to 0.24.1, partition_html(html_parser_version=\"v2\") and the VLM partitioner can preserve untrusted document tags, attributes, text, and link targets in metadata.text_as_html, while elements_to_html() emits the result as an HTML document. The to_html() path in unstructured/documents/ontology.py does not escape output or reject unsafe URL schemes, allowing event-handler attributes, attribute breakout markup, and javascript: links to survive parsing. When the generated HTML or text_as_html is rendered in a browser, attacker-controlled script can execute in the viewer\u0027s origin, including in document-ingestion workflows where a privileged reviewer opens submitted content. This issue is fixed in version 0.24.1."
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "NONE",
"baseScore": 6.1,
"baseSeverity": "MEDIUM",
"confidentialityImpact": "LOW",
"integrityImpact": "LOW",
"privilegesRequired": "NONE",
"scope": "CHANGED",
"userInteraction": "REQUIRED",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:L/I:L/A:N",
"version": "3.1"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-79",
"description": "CWE-79: Improper Neutralization of Input During Web Page Generation (\u0027Cross-site Scripting\u0027)",
"lang": "en",
"type": "CWE"
}
]
},
{
"descriptions": [
{
"cweId": "CWE-116",
"description": "CWE-116: Improper Encoding or Escaping of Output",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-10-13T16:29:28.813Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/Unstructured-IO/unstructured/security/advisories/GHSA-v5mq-3xhg-98m9",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/Unstructured-IO/unstructured/security/advisories/GHSA-v5mq-3xhg-98m9"
},
{
"name": "https://github.com/Unstructured-IO/unstructured/pull/4394",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/Unstructured-IO/unstructured/pull/4394"
},
{
"name": "https://github.com/Unstructured-IO/unstructured/commit/cda16b3f2170019be9c6ea5635946fb3eaa2d66f",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/Unstructured-IO/unstructured/commit/cda16b3f2170019be9c6ea5635946fb3eaa2d66f"
},
{
"name": "https://github.com/Unstructured-IO/unstructured/releases/tag/0.24.1",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/Unstructured-IO/unstructured/releases/tag/0.24.1"
}
],
"source": {
"advisory": "GHSA-v5mq-3xhg-98m9",
"discovery": "UNKNOWN"
},
"title": "unstructured: Stored XSS via unescaped HTML generation"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2026-104250",
"datePublished": "2026-10-13T16:29:28.813Z",
"dateReserved": "2026-10-01T19:04:39.706Z",
"dateUpdated": "2026-10-14T15:32:42.130Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2026-71428 (GCVE-0-2026-71428)
Vulnerability from cvelistv5 – Published: 2026-08-20 16:43 – Updated: 2026-08-25 15:05
VLAI
EPSS
VEX
Title
unstructured: Server-Side Request Forgery in the URL-based partitioning
Summary
The unstructured library provides open-source components for ingesting and pre-processing images and text documents, such as PDFs, HTML, Word docs, and many more. From 0.4.7 until 0.24.0, the url argument of partition, partition_html, and partition_md is fetched without host validation in unstructured/partition/auto.py, unstructured/partition/html/partition.py, and unstructured/partition/md.py. An attacker who controls that URL can make a server-side ingestion service request loopback addresses, internal HTTP services, or cloud metadata endpoints through direct targets, redirects, or DNS rebinding. The response body is returned as Element text, allowing internal response disclosure, and side-effecting GET endpoints may also be triggered. This issue is fixed in version 0.24.0.
Severity
9.3 (Critical)
SSVC
Exploitation: poc
Automatable: yes
Technical Impact: partial
CISA Coordinator · CISA-ADP (v2.0.3)
Decision recorded 2026-08-25 15:05 UTC
CWE
Assigner
References
4 references
| URL | Tags |
|---|---|
| https://github.com/Unstructured-IO/unstructured/s… | x_refsource_CONFIRM |
| https://github.com/Unstructured-IO/unstructured/p… | x_refsource_MISC |
| https://github.com/Unstructured-IO/unstructured/c… | x_refsource_MISC |
| https://github.com/Unstructured-IO/unstructured/r… | x_refsource_MISC |
Impacted products
1 product
| Vendor | Product | Version | |
|---|---|---|---|
| Unstructured-IO | unstructured |
Affected:
>= 0.4.7, < 0.24.0
|
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-71428",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "yes"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-08-25T15:05:06.666433Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-08-25T15:05:17.185Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "unstructured",
"vendor": "Unstructured-IO",
"versions": [
{
"status": "affected",
"version": "\u003e= 0.4.7, \u003c 0.24.0"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "The unstructured library provides open-source components for ingesting and pre-processing images and text documents, such as PDFs, HTML, Word docs, and many more. From 0.4.7 until 0.24.0, the url argument of partition, partition_html, and partition_md is fetched without host validation in unstructured/partition/auto.py, unstructured/partition/html/partition.py, and unstructured/partition/md.py. An attacker who controls that URL can make a server-side ingestion service request loopback addresses, internal HTTP services, or cloud metadata endpoints through direct targets, redirects, or DNS rebinding. The response body is returned as Element text, allowing internal response disclosure, and side-effecting GET endpoints may also be triggered. This issue is fixed in version 0.24.0."
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "NONE",
"baseScore": 9.3,
"baseSeverity": "CRITICAL",
"confidentialityImpact": "HIGH",
"integrityImpact": "LOW",
"privilegesRequired": "NONE",
"scope": "CHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:L/A:N",
"version": "3.1"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-601",
"description": "CWE-601: URL Redirection to Untrusted Site (\u0027Open Redirect\u0027)",
"lang": "en",
"type": "CWE"
}
]
},
{
"descriptions": [
{
"cweId": "CWE-918",
"description": "CWE-918: Server-Side Request Forgery (SSRF)",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-08-20T16:43:01.306Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/Unstructured-IO/unstructured/security/advisories/GHSA-4mvj-m6j5-pmf7",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/Unstructured-IO/unstructured/security/advisories/GHSA-4mvj-m6j5-pmf7"
},
{
"name": "https://github.com/Unstructured-IO/unstructured/pull/4388",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/Unstructured-IO/unstructured/pull/4388"
},
{
"name": "https://github.com/Unstructured-IO/unstructured/commit/445c95735c4045057f51f399bc04c657751923bd",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/Unstructured-IO/unstructured/commit/445c95735c4045057f51f399bc04c657751923bd"
},
{
"name": "https://github.com/Unstructured-IO/unstructured/releases/tag/0.24.0",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/Unstructured-IO/unstructured/releases/tag/0.24.0"
}
],
"source": {
"advisory": "GHSA-4mvj-m6j5-pmf7",
"discovery": "UNKNOWN"
},
"title": "unstructured: Server-Side Request Forgery in the URL-based partitioning"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2026-71428",
"datePublished": "2026-08-20T16:43:01.306Z",
"dateReserved": "2026-08-06T16:28:51.182Z",
"dateUpdated": "2026-08-25T15:05:17.185Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2025-64712 (GCVE-0-2025-64712)
Vulnerability from cvelistv5 – Published: 2026-02-04 17:34 – Updated: 2026-02-04 19:24
VLAI
EPSS
VEX
Title
Unstructured has Path Traversal via Malicious MSG Attachment that Allows Arbitrary File Write
Summary
The unstructured library provides open-source components for ingesting and pre-processing images and text documents, such as PDFs, HTML, Word docs, and many more. Prior to version 0.18.18, a path traversal vulnerability in the partition_msg function allows an attacker to write or overwrite arbitrary files on the filesystem when processing malicious MSG files with attachments. This issue has been patched in version 0.18.18.
Severity
9.8 (Critical)
SSVC
Exploitation: none
Automatable: yes
Technical Impact: total
CISA Coordinator · CISA-ADP (v2.0.3)
Decision recorded 2026-02-04 19:24 UTC
CWE
Assigner
References
2 references
| URL | Tags |
|---|---|
| https://github.com/Unstructured-IO/unstructured/s… | x_refsource_CONFIRM |
| https://github.com/Unstructured-IO/unstructured/c… | x_refsource_MISC |
Impacted products
1 product
| Vendor | Product | Version | |
|---|---|---|---|
| Unstructured-IO | unstructured |
Affected:
< 0.18.18
|
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2025-64712",
"options": [
{
"Exploitation": "none"
},
{
"Automatable": "yes"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-02-04T19:24:03.397110Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-02-04T19:24:12.411Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "unstructured",
"vendor": "Unstructured-IO",
"versions": [
{
"status": "affected",
"version": "\u003c 0.18.18"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "The unstructured library provides open-source components for ingesting and pre-processing images and text documents, such as PDFs, HTML, Word docs, and many more. Prior to version 0.18.18, a path traversal vulnerability in the partition_msg function allows an attacker to write or overwrite arbitrary files on the filesystem when processing malicious MSG files with attachments. This issue has been patched in version 0.18.18."
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "HIGH",
"baseScore": 9.8,
"baseSeverity": "CRITICAL",
"confidentialityImpact": "HIGH",
"integrityImpact": "HIGH",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H",
"version": "3.1"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-22",
"description": "CWE-22: Improper Limitation of a Pathname to a Restricted Directory (\u0027Path Traversal\u0027)",
"lang": "en",
"type": "CWE"
}
]
},
{
"descriptions": [
{
"cweId": "CWE-73",
"description": "CWE-73: External Control of File Name or Path",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-02-04T17:34:51.426Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/Unstructured-IO/unstructured/security/advisories/GHSA-gm8q-m8mv-jj5m",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/Unstructured-IO/unstructured/security/advisories/GHSA-gm8q-m8mv-jj5m"
},
{
"name": "https://github.com/Unstructured-IO/unstructured/commit/b01d35b2373fd087d2e15162b9c021663c97155d",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/Unstructured-IO/unstructured/commit/b01d35b2373fd087d2e15162b9c021663c97155d"
}
],
"source": {
"advisory": "GHSA-gm8q-m8mv-jj5m",
"discovery": "UNKNOWN"
},
"title": "Unstructured has Path Traversal via Malicious MSG Attachment that Allows Arbitrary File Write"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2025-64712",
"datePublished": "2026-02-04T17:34:51.426Z",
"dateReserved": "2025-11-10T14:07:42.921Z",
"dateUpdated": "2026-02-04T19:24:12.411Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}