{"id":"CVE-2026-88052","state":"PUBLISHED","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.","publishedAt":"2026-09-10T17:38:04.675Z","updatedAt":"2026-09-11T20:33:04.012Z","severity":{"score":7.8,"label":"High","version":"3.1","vector":"CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H","source":"GitHub_M"},"assigner":"GitHub_M","products":["tesseract-ocr tesseract"],"affected":[{"vendor":"tesseract-ocr","product":"tesseract","versions":[{"version":"<= 5.5.3","status":"affected"}]}],"references":["https://github.com/tesseract-ocr/tesseract/security/advisories/GHSA-2hm8-q5c7-c373","https://github.com/tesseract-ocr/tesseract/commit/2d04d640db2e8c7e3bab2369d599343b5a8b8443"],"weaknesses":["CWE-129","CWE-787"],"ingestedAt":"2026-10-29T20:13:26.108Z","source":{"repository":"CVEProject/cvelistV5","path":"cves/2026/88xxx/CVE-2026-88052.json","commit":"556c9d3a8cd17e218bb8e452ba7cd619a384ff47"},"raw":{"dataType":"CVE_RECORD","dataVersion":"5.2","cveMetadata":{"cveId":"CVE-2026-88052","state":"PUBLISHED","datePublished":"2026-09-10T17:38:04.675Z","dateUpdated":"2026-09-11T20:33:04.012Z","assignerShortName":"GitHub_M","assignerOrgId":"a0819718-46f1-4df5-94e2-005712e83aaa","dateReserved":"2026-09-09T21:22:45.433Z"},"containers":{"cna":{"title":"Tesseract: Heap out-of-bounds write in UNICHARSET::load_via_fgets via count/insert desynchronization","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."}],"affected":[{"vendor":"tesseract-ocr","product":"tesseract","versions":[{"version":"<= 5.5.3","status":"affected"}]}],"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","tags":["x_refsource_CONFIRM"]},{"url":"https://github.com/tesseract-ocr/tesseract/commit/2d04d640db2e8c7e3bab2369d599343b5a8b8443","name":"https://github.com/tesseract-ocr/tesseract/commit/2d04d640db2e8c7e3bab2369d599343b5a8b8443","tags":["x_refsource_MISC"]}],"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","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"}]}],"providerMetadata":{"shortName":"GitHub_M","orgId":"a0819718-46f1-4df5-94e2-005712e83aaa","dateUpdated":"2026-09-10T17:38:04.675Z"},"source":{"advisory":"GHSA-2hm8-q5c7-c373","discovery":"UNKNOWN"}},"adp":[{"title":"CISA ADP Vulnrichment","metrics":[{"other":{"type":"ssvc","content":{"timestamp":"2026-09-11T16:48:33.418715Z","id":"CVE-2026-88052","options":[{"Exploitation":"none"},{"Automatable":"no"},{"Technical Impact":"total"}],"role":"CISA Coordinator","version":"2.0.3"}}}],"providerMetadata":{"shortName":"CISA-ADP","orgId":"134c704f-9b21-4f2e-91b3-4a467353bcc0","dateUpdated":"2026-09-11T20:33:04.012Z"}}]}}}