{"dataType": "CVE_RECORD", "dataVersion": "5.2", "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": "2026-10-13T16:29:28.813Z"}, "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 ('Cross-site Scripting')", "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": "< 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's 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"}}}}

{}

{"affected": [{"affectedData": [{"product": "unstructured", "vendor": "Unstructured-IO", "versions": [{"status": "affected", "version": "< 0.24.1"}]}], "source": "[email protected]"}], "cveTags": [], "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's origin, including in document-ingestion workflows where a privileged reviewer opens submitted content. This issue is fixed in version 0.24.1."}], "id": "CVE-2026-104250", "lastModified": "2026-10-13T17:17:15.900", "metrics": {"cvssMetricV31": [{"cvssData": {"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"}, "exploitabilityScore": 2.8, "impactScore": 2.7, "source": "[email protected]", "type": "Secondary"}]}, "published": "2026-10-13T17:17:15.900", "references": [{"source": "[email protected]", "url": "https://github.com/Unstructured-IO/unstructured/commit/cda16b3f2170019be9c6ea5635946fb3eaa2d66f"}, {"source": "[email protected]", "url": "https://github.com/Unstructured-IO/unstructured/pull/4394"}, {"source": "[email protected]", "url": "https://github.com/Unstructured-IO/unstructured/releases/tag/0.24.1"}, {"source": "[email protected]", "url": "https://github.com/Unstructured-IO/unstructured/security/advisories/GHSA-v5mq-3xhg-98m9"}], "sourceIdentifier": "[email protected]", "vulnStatus": "Received", "weaknesses": [{"description": [{"lang": "en", "value": "CWE-79"}, {"lang": "en", "value": "CWE-116"}], "source": "[email protected]", "type": "Primary"}]}

{}

{"affected": [{"configurations": [{"platform": null, "status": "affected", "versions": {"scheme": "semver", "value": "[0,0.24.1)"}}], "enrichment": {"confidence": 100.0, "confidence_source": "matching", "scores": [{"score": 100.0, "source": "matching"}]}, "original": {"product": "unstructured", "source": "cna", "vendor": "Unstructured-IO"}, "product": "unstructured", "vendor": "unstructured-io"}], "created": "2026-10-13T18:00:07.771416+00:00", "updated": "2026-10-13T18:45:15.201158+00:00", "vendors": ["unstructured-io", "unstructured-io$PRODUCT$unstructured"]}