{"id":"CVE-2026-88050","state":"PUBLISHED","title":"Tesseract: Out-of-bounds write in UnicharCompress via unvalidated recoder code values","description":"Tesseract is an open source OCR engine. In version 5.5.3 and earlier, RecodedCharID::DeSerialize in src/ccutil/unicharcompress.h validates length_ but accepts negative code_ values from a crafted .traineddata recoder component. UnicharCompress::ComputeCodeRange in src/ccutil/unicharcompress.cpp can consequently produce code_range_ equal to zero, after which SetupDecoder indexes is_valid_start_ with the negative code on a size-zero vector. The resulting out-of-bounds bit write uses a large wrapped index and reliably causes a wild-address crash or allocation failure on the default LSTM engine. No fixed release is available as of this review.","publishedAt":"2026-09-10T16:24:21.331Z","updatedAt":"2026-09-10T17:30:29.252Z","severity":{"score":6.9,"label":"Medium","version":"4.0","vector":"CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/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-7v9h-3q3m-w68g","https://github.com/tesseract-ocr/tesseract/commit/c94a5532ee04db5a4919542832fd94caee5ea58f"],"weaknesses":["CWE-787"],"ingestedAt":"2026-10-29T20:13:26.108Z","source":{"repository":"CVEProject/cvelistV5","path":"cves/2026/88xxx/CVE-2026-88050.json","commit":"556c9d3a8cd17e218bb8e452ba7cd619a384ff47"},"raw":{"dataType":"CVE_RECORD","dataVersion":"5.2","cveMetadata":{"cveId":"CVE-2026-88050","state":"PUBLISHED","datePublished":"2026-09-10T16:24:21.331Z","dateUpdated":"2026-09-10T17:30:29.252Z","assignerShortName":"GitHub_M","assignerOrgId":"a0819718-46f1-4df5-94e2-005712e83aaa","dateReserved":"2026-09-09T21:22:45.433Z"},"containers":{"cna":{"title":"Tesseract: Out-of-bounds write in UnicharCompress via unvalidated recoder code values","descriptions":[{"lang":"en","value":"Tesseract is an open source OCR engine. In version 5.5.3 and earlier, RecodedCharID::DeSerialize in src/ccutil/unicharcompress.h validates length_ but accepts negative code_ values from a crafted .traineddata recoder component. UnicharCompress::ComputeCodeRange in src/ccutil/unicharcompress.cpp can consequently produce code_range_ equal to zero, after which SetupDecoder indexes is_valid_start_ with the negative code on a size-zero vector. The resulting out-of-bounds bit write uses a large wrapped index and reliably causes a wild-address crash or allocation failure on the default LSTM engine. 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-7v9h-3q3m-w68g","name":"https://github.com/tesseract-ocr/tesseract/security/advisories/GHSA-7v9h-3q3m-w68g","tags":["x_refsource_CONFIRM"]},{"url":"https://github.com/tesseract-ocr/tesseract/commit/c94a5532ee04db5a4919542832fd94caee5ea58f","name":"https://github.com/tesseract-ocr/tesseract/commit/c94a5532ee04db5a4919542832fd94caee5ea58f","tags":["x_refsource_MISC"]}],"metrics":[{"cvssV4_0":{"attackVector":"LOCAL","attackComplexity":"LOW","attackRequirements":"NONE","privilegesRequired":"NONE","userInteraction":"NONE","vulnConfidentialityImpact":"NONE","vulnIntegrityImpact":"NONE","vulnAvailabilityImpact":"HIGH","subConfidentialityImpact":"NONE","subIntegrityImpact":"NONE","subAvailabilityImpact":"NONE","baseScore":6.9,"baseSeverity":"MEDIUM","vectorString":"CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/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":"2026-09-10T16:24:21.331Z"},"source":{"advisory":"GHSA-7v9h-3q3m-w68g","discovery":"UNKNOWN"}},"adp":[{"title":"CISA ADP Vulnrichment","references":[{"url":"https://github.com/tesseract-ocr/tesseract/security/advisories/GHSA-7v9h-3q3m-w68g","tags":["exploit"]}],"metrics":[{"other":{"type":"ssvc","content":{"timestamp":"2026-09-10T17:28:04.777181Z","id":"CVE-2026-88050","options":[{"Exploitation":"poc"},{"Automatable":"no"},{"Technical Impact":"partial"}],"role":"CISA Coordinator","version":"2.0.3"}}}],"providerMetadata":{"shortName":"CISA-ADP","orgId":"134c704f-9b21-4f2e-91b3-4a467353bcc0","dateUpdated":"2026-09-10T17:30:29.252Z"}}]}}}