{"dataType": "CVE_RECORD", "dataVersion": "5.2", "cveMetadata": {"cveId": "CVE-2026-88052", "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa", "state": "PUBLISHED", "assignerShortName": "GitHub_M", "dateReserved": "2026-09-09T21:22:45.433Z", "datePublished": "2026-09-10T17:38:04.675Z", "dateUpdated": "2026-09-10T17:38:04.675Z"}, "containers": {"cna": {"title": "Tesseract: Heap out-of-bounds write in UNICHARSET::load_via_fgets via count/insert desynchronization", "problemTypes": [{"descriptions": [{"cweId": "CWE-129", "lang": "en", "description": "CWE-129: Improper Validation of Array Index", "type": "CWE"}]}, {"descriptions": [{"cweId": "CWE-787", "lang": "en", "description": "CWE-787: Out-of-bounds Write", "type": "CWE"}]}], "metrics": [{"cvssV3_1": {"attackComplexity": "LOW", "attackVector": "LOCAL", "availabilityImpact": "HIGH", "baseScore": 7.8, "baseSeverity": "HIGH", "confidentialityImpact": "HIGH", "integrityImpact": "HIGH", "privilegesRequired": "NONE", "scope": "UNCHANGED", "userInteraction": "REQUIRED", "vectorString": "CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H", "version": "3.1"}}], "references": [{"name": "https://github.com/tesseract-ocr/tesseract/security/advisories/GHSA-2hm8-q5c7-c373", "tags": ["x_refsource_CONFIRM"], "url": "https://github.com/tesseract-ocr/tesseract/security/advisories/GHSA-2hm8-q5c7-c373"}, {"name": "https://github.com/tesseract-ocr/tesseract/commit/2d04d640db2e8c7e3bab2369d599343b5a8b8443", "tags": ["x_refsource_MISC"], "url": "https://github.com/tesseract-ocr/tesseract/commit/2d04d640db2e8c7e3bab2369d599343b5a8b8443"}], "affected": [{"vendor": "tesseract-ocr", "product": "tesseract", "versions": [{"version": "<= 5.5.3", "status": "affected"}]}], "providerMetadata": {"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa", "shortName": "GitHub_M", "dateUpdated": "2026-09-10T17:38:04.675Z"}, "descriptions": [{"lang": "en", "value": "Tesseract is an open source OCR engine. In version 5.5.3 and earlier, UNICHARSET::load_via_fgets in src/ccutil/unicharset.cpp trusts the declared unichar count as a loop bound and uses id as an unchecked index into the unichars vector. unichar_insert_backwards_compatible can leave the vector unchanged for an empty, duplicate, or already-encodable representation, causing id to become larger than unichars.size(). Subsequent set_* calls and the write to unichars[id].properties.enabled then write UNICHAR_PROPERTIES beyond the vector during initialization in both the default LSTM and legacy engines, causing heap corruption, a crash, or potentially controlled corruption. No fixed release is available as of this review."}], "source": {"advisory": "GHSA-2hm8-q5c7-c373", "discovery": "UNKNOWN"}}}}

{}

{}

{}

{}