CVE-2026-104250 (GCVE-0-2026-104250)
Vulnerability from cvelistv5
Published
2026-10-13 16:29
Modified
2026-10-14 15:32
Severity ?
VLAI Severity ?
EPSS score ?
CWE
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.
References
| URL | Tags | |
|---|---|---|
|
|
||
Impacted products
| Vendor | Product | Version | ||
|---|---|---|---|---|
| Unstructured-IO | unstructured |
Version: < 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",
"vulnerability-lookup:meta": {
"vulnrichment": {
"containers": "{\"cna\": {\"title\": \"unstructured: Stored XSS via unescaped HTML generation\", \"problemTypes\": [{\"descriptions\": [{\"cweId\": \"CWE-79\", \"lang\": \"en\", \"description\": \"CWE-79: Improper Neutralization of Input During Web Page Generation (\u0027Cross-site Scripting\u0027)\", \"type\": \"CWE\"}]}, {\"descriptions\": [{\"cweId\": \"CWE-116\", \"lang\": \"en\", \"description\": \"CWE-116: Improper Encoding or Escaping of Output\", \"type\": \"CWE\"}]}], \"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\"}}], \"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\"}], \"affected\": [{\"vendor\": \"Unstructured-IO\", \"product\": \"unstructured\", \"versions\": [{\"version\": \"\u003c 0.24.1\", \"status\": \"affected\"}]}], \"providerMetadata\": {\"orgId\": \"a0819718-46f1-4df5-94e2-005712e83aaa\", \"shortName\": \"GitHub_M\", \"dateUpdated\": \"2026-10-13T16:29:28.813Z\"}, \"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.\"}], \"source\": {\"advisory\": \"GHSA-v5mq-3xhg-98m9\", \"discovery\": \"UNKNOWN\"}}, \"adp\": [{\"title\": \"CISA ADP Vulnrichment\", \"metrics\": [{\"other\": {\"type\": \"ssvc\", \"content\": {\"id\": \"CVE-2026-104250\", \"role\": \"CISA Coordinator\", \"options\": [{\"Exploitation\": \"poc\"}, {\"Automatable\": \"no\"}, {\"Technical Impact\": \"partial\"}], \"version\": \"2.0.3\", \"timestamp\": \"2026-10-14T15:32:11.460266Z\"}}}], \"references\": [{\"url\": \"https://github.com/Unstructured-IO/unstructured/security/advisories/GHSA-v5mq-3xhg-98m9\", \"tags\": [\"exploit\"]}], \"providerMetadata\": {\"orgId\": \"134c704f-9b21-4f2e-91b3-4a467353bcc0\", \"shortName\": \"CISA-ADP\", \"dateUpdated\": \"2026-10-14T15:32:26.141Z\"}}]}",
"cveMetadata": "{\"cveId\": \"CVE-2026-104250\", \"assignerOrgId\": \"a0819718-46f1-4df5-94e2-005712e83aaa\", \"state\": \"PUBLISHED\", \"assignerShortName\": \"GitHub_M\", \"dateReserved\": \"2026-10-01T19:04:39.706Z\", \"datePublished\": \"2026-10-13T16:29:28.813Z\", \"dateUpdated\": \"2026-10-14T15:32:42.130Z\"}",
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
}
}
Loading…
Loading…
Sightings
| Author | Source | Type | Date |
|---|
Nomenclature
- Seen: The vulnerability was mentioned, discussed, or seen somewhere by the user.
- Confirmed: The vulnerability is confirmed from an analyst perspective.
- Published Proof of Concept: A public proof of concept is available for this vulnerability.
- Exploited: This vulnerability was exploited and seen by the user reporting the sighting.
- Patched: This vulnerability was successfully patched by the user reporting the sighting.
- Not exploited: This vulnerability was not exploited or seen by the user reporting the sighting.
- Not confirmed: The user expresses doubt about the veracity of the vulnerability.
- Not patched: This vulnerability was not successfully patched by the user reporting the sighting.
Loading…
Loading…