{"api_version":"1","generated_at":"2026-09-11T00:21:18+00:00","cve":"CVE-2026-88052","urls":{"html":"https://cve.report/CVE-2026-88052","api":"https://cve.report/api/cve/CVE-2026-88052.json","docs":"https://cve.report/api","cve_org":"https://www.cve.org/CVERecord?id=CVE-2026-88052","nvd":"https://nvd.nist.gov/vuln/detail/CVE-2026-88052"},"summary":{"title":"Tesseract: Heap out-of-bounds write in UNICHARSET::load_via_fgets via count/insert desynchronization","description":"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.","state":"PUBLISHED","assigner":"GitHub_M","published_at":"2026-09-10 18:18:14","updated_at":"2026-09-10 19:54:25"},"problem_types":["CWE-129","CWE-787","CWE-129 CWE-129: Improper Validation of Array Index","CWE-787 CWE-787: Out-of-bounds Write"],"metrics":[{"version":"3.1","source":"security-advisories@github.com","type":"Secondary","score":"7.8","severity":"HIGH","vector":"CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H","data":{"version":"3.1","vectorString":"CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H","baseScore":7.8,"baseSeverity":"HIGH","attackVector":"LOCAL","attackComplexity":"LOW","privilegesRequired":"NONE","userInteraction":"REQUIRED","scope":"UNCHANGED","confidentialityImpact":"HIGH","integrityImpact":"HIGH","availabilityImpact":"HIGH"}},{"version":"3.1","source":"CNA","type":"DECLARED","score":"7.8","severity":"HIGH","vector":"CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H","data":{"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":[{"url":"https://github.com/tesseract-ocr/tesseract/security/advisories/GHSA-2hm8-q5c7-c373","name":"https://github.com/tesseract-ocr/tesseract/security/advisories/GHSA-2hm8-q5c7-c373","refsource":"security-advisories@github.com","tags":[],"title":"","mime":"","httpstatus":"","archivestatus":"0"},{"url":"https://github.com/tesseract-ocr/tesseract/commit/2d04d640db2e8c7e3bab2369d599343b5a8b8443","name":"https://github.com/tesseract-ocr/tesseract/commit/2d04d640db2e8c7e3bab2369d599343b5a8b8443","refsource":"security-advisories@github.com","tags":[],"title":"","mime":"","httpstatus":"","archivestatus":"0"},{"url":"https://www.cve.org/CVERecord?id=CVE-2026-88052","name":"CVE Program record","refsource":"CVE.ORG","tags":["canonical"]},{"url":"https://nvd.nist.gov/vuln/detail/CVE-2026-88052","name":"NVD vulnerability detail","refsource":"NVD","tags":["canonical","analysis"]}],"affected":[{"source":"CNA","vendor":"tesseract-ocr","product":"tesseract","version":"affected <= 5.5.3","platforms":[]}],"timeline":[],"solutions":[],"workarounds":[],"exploits":[],"credits":[],"nvd_cpes":[],"vendor_comments":[],"enrichments":{"kev":null,"epss":null,"legacy_qids":[]},"source_records":{"cve_program":{"containers":{"cna":{"affected":[{"product":"tesseract","vendor":"tesseract-ocr","versions":[{"status":"affected","version":"<= 5.5.3"}]}],"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."}],"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"}}],"problemTypes":[{"descriptions":[{"cweId":"CWE-129","description":"CWE-129: Improper Validation of Array Index","lang":"en","type":"CWE"}]},{"descriptions":[{"cweId":"CWE-787","description":"CWE-787: Out-of-bounds Write","lang":"en","type":"CWE"}]}],"providerMetadata":{"dateUpdated":"2026-09-10T17:38:04.675Z","orgId":"a0819718-46f1-4df5-94e2-005712e83aaa","shortName":"GitHub_M"},"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"}],"source":{"advisory":"GHSA-2hm8-q5c7-c373","discovery":"UNKNOWN"},"title":"Tesseract: Heap out-of-bounds write in UNICHARSET::load_via_fgets via count/insert desynchronization"}},"cveMetadata":{"assignerOrgId":"a0819718-46f1-4df5-94e2-005712e83aaa","assignerShortName":"GitHub_M","cveId":"CVE-2026-88052","datePublished":"2026-09-10T17:38:04.675Z","dateReserved":"2026-09-09T21:22:45.433Z","dateUpdated":"2026-09-10T17:38:04.675Z","state":"PUBLISHED"},"dataType":"CVE_RECORD","dataVersion":"5.2"},"nvd":{"publishedDate":"2026-09-10 18:18:14","lastModifiedDate":"2026-09-10 19:54:25","problem_types":["CWE-129","CWE-787","CWE-129 CWE-129: Improper Validation of Array Index","CWE-787 CWE-787: Out-of-bounds Write"],"metrics":{"cvssMetricV31":[{"source":"security-advisories@github.com","type":"Secondary","cvssData":{"version":"3.1","vectorString":"CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H","baseScore":7.8,"baseSeverity":"HIGH","attackVector":"LOCAL","attackComplexity":"LOW","privilegesRequired":"NONE","userInteraction":"REQUIRED","scope":"UNCHANGED","confidentialityImpact":"HIGH","integrityImpact":"HIGH","availabilityImpact":"HIGH"},"exploitabilityScore":1.8,"impactScore":5.9}]},"configurations":[]},"legacy_mitre":{"record":{"CveYear":"2026","CveId":"88052","Ordinal":"1","Title":"Tesseract: Heap out-of-bounds write in UNICHARSET::load_via_fget","CVE":"CVE-2026-88052","Year":"2026"},"notes":[{"CveYear":"2026","CveId":"88052","Ordinal":"1","NoteData":"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.","Type":"Description","Title":"Tesseract: Heap out-of-bounds write in UNICHARSET::load_via_fget"}]}}}