{"id":"CVE-2026-88053","state":"PUBLISHED","title":"Tesseract: Heap out-of-bounds write in Classify::ReadIntTemplates via unvalidated counts in crafted .traineddata","description":"Tesseract is an open source OCR engine. In version 5.5.3 and earlier, Classify::ReadIntTemplates in src/classify/intproto.cpp reads NumClassPruners, NumClasses, and NumProtoSets from the TESSDATA_INTTEMP component of a crafted .traineddata file and uses those values as loop bounds without validating them against MAX_NUM_CLASS_PRUNERS, MAX_NUM_CLASSES, and MAX_NUM_PROTO_SETS. The loops store heap pointers into fixed-capacity ClassPruners and ProtoSets arrays in INT_TEMPLATES_STRUCT and INT_CLASS_STRUCT, so an oversized count causes heap out-of-bounds pointer writes during legacy-classifier initialization before OCR begins, resulting in heap corruption, a crash, or potentially controlled corruption. No fixed release is available as of this review.","publishedAt":"2026-09-10T17:38:58.271Z","updatedAt":"2026-09-11T15:58:00.968Z","severity":{"score":8.6,"label":"High","version":"4.0","vector":"CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N","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-rphx-x795-5qjv","https://github.com/tesseract-ocr/tesseract/commit/8b0574680f3b22f246ade6a4c8e3029104255c63"],"weaknesses":["CWE-787"],"ingestedAt":"2026-10-29T20:13:26.108Z","source":{"repository":"CVEProject/cvelistV5","path":"cves/2026/88xxx/CVE-2026-88053.json","commit":"556c9d3a8cd17e218bb8e452ba7cd619a384ff47"},"raw":{"dataType":"CVE_RECORD","dataVersion":"5.2","cveMetadata":{"cveId":"CVE-2026-88053","state":"PUBLISHED","datePublished":"2026-09-10T17:38:58.271Z","dateUpdated":"2026-09-11T15:58:00.968Z","assignerShortName":"GitHub_M","assignerOrgId":"a0819718-46f1-4df5-94e2-005712e83aaa","dateReserved":"2026-09-09T21:22:45.434Z"},"containers":{"cna":{"title":"Tesseract: Heap out-of-bounds write in Classify::ReadIntTemplates via unvalidated counts in crafted .traineddata","descriptions":[{"lang":"en","value":"Tesseract is an open source OCR engine. In version 5.5.3 and earlier, Classify::ReadIntTemplates in src/classify/intproto.cpp reads NumClassPruners, NumClasses, and NumProtoSets from the TESSDATA_INTTEMP component of a crafted .traineddata file and uses those values as loop bounds without validating them against MAX_NUM_CLASS_PRUNERS, MAX_NUM_CLASSES, and MAX_NUM_PROTO_SETS. The loops store heap pointers into fixed-capacity ClassPruners and ProtoSets arrays in INT_TEMPLATES_STRUCT and INT_CLASS_STRUCT, so an oversized count causes heap out-of-bounds pointer writes during legacy-classifier initialization before OCR begins, resulting in 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-rphx-x795-5qjv","name":"https://github.com/tesseract-ocr/tesseract/security/advisories/GHSA-rphx-x795-5qjv","tags":["x_refsource_CONFIRM"]},{"url":"https://github.com/tesseract-ocr/tesseract/commit/8b0574680f3b22f246ade6a4c8e3029104255c63","name":"https://github.com/tesseract-ocr/tesseract/commit/8b0574680f3b22f246ade6a4c8e3029104255c63","tags":["x_refsource_MISC"]}],"metrics":[{"cvssV4_0":{"attackVector":"LOCAL","attackComplexity":"LOW","attackRequirements":"NONE","privilegesRequired":"NONE","userInteraction":"NONE","vulnConfidentialityImpact":"HIGH","vulnIntegrityImpact":"HIGH","vulnAvailabilityImpact":"HIGH","subConfidentialityImpact":"NONE","subIntegrityImpact":"NONE","subAvailabilityImpact":"NONE","baseScore":8.6,"baseSeverity":"HIGH","vectorString":"CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N","version":"4.0"}}],"problemTypes":[{"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":"2026-09-10T17:38:58.271Z"},"source":{"advisory":"GHSA-rphx-x795-5qjv","discovery":"UNKNOWN"}},"adp":[{"title":"CISA ADP Vulnrichment","references":[{"url":"https://github.com/tesseract-ocr/tesseract/security/advisories/GHSA-rphx-x795-5qjv","tags":["exploit"]}],"metrics":[{"other":{"type":"ssvc","content":{"timestamp":"2026-09-11T15:57:52.566515Z","id":"CVE-2026-88053","options":[{"Exploitation":"poc"},{"Automatable":"no"},{"Technical Impact":"total"}],"role":"CISA Coordinator","version":"2.0.3"}}}],"providerMetadata":{"shortName":"CISA-ADP","orgId":"134c704f-9b21-4f2e-91b3-4a467353bcc0","dateUpdated":"2026-09-11T15:58:00.968Z"}}]}}}