{"dataType":"CVE_RECORD","dataVersion":"5.2","cveMetadata":{"cveId":"CVE-2026-88047","assignerOrgId":"a0819718-46f1-4df5-94e2-005712e83aaa","state":"PUBLISHED","assignerShortName":"GitHub_M","dateReserved":"2026-09-09T21:22:45.433Z","datePublished":"2026-09-10T16:18:01.588Z","dateUpdated":"2026-09-11T20:33:10.471Z"},"containers":{"cna":{"title":"Tesseract: ReadNormProtos stack buffer overflow","problemTypes":[{"descriptions":[{"cweId":"CWE-121","lang":"en","description":"CWE-121: Stack-based Buffer Overflow","type":"CWE"}]}],"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"}}],"references":[{"name":"https://github.com/tesseract-ocr/tesseract/security/advisories/GHSA-5j2p-r5vc-q7f3","tags":["x_refsource_CONFIRM"],"url":"https://github.com/tesseract-ocr/tesseract/security/advisories/GHSA-5j2p-r5vc-q7f3"},{"name":"https://github.com/tesseract-ocr/tesseract/commit/1bda5079b1c8a7e25f523486837426903d29ce84","tags":["x_refsource_MISC"],"url":"https://github.com/tesseract-ocr/tesseract/commit/1bda5079b1c8a7e25f523486837426903d29ce84"}],"affected":[{"vendor":"tesseract-ocr","product":"tesseract","versions":[{"version":"<= 5.5.3","status":"affected"}]}],"providerMetadata":{"orgId":"a0819718-46f1-4df5-94e2-005712e83aaa","shortName":"GitHub_M","dateUpdated":"2026-09-10T16:18:01.588Z"},"descriptions":[{"lang":"en","value":"Tesseract is an open source OCR engine. In version 5.5.3 and earlier, Classify::ReadNormProtos in src/classify/normmatch.cpp parses the NORMPROTO component of a .traineddata file and uses std::istream::operator>>(char*) to extract a whitespace-delimited token into a fixed 61-byte stack buffer without setting a stream width. The 100-byte line buffer can carry a token of up to 99 characters, so a token longer than 60 characters writes up to 39 attacker-controlled bytes past the buffer during TessBaseAPI::Init of the legacy engine, causing stack corruption, denial of service, and potentially control-flow hijacking on affected standard-library implementations. Builds using Apple's libc++ C++20 bounded array overload are incidentally protected, while typical libstdc++ builds remain affected. No fixed release is available as of this review."}],"source":{"advisory":"GHSA-5j2p-r5vc-q7f3","discovery":"UNKNOWN"}},"adp":[{"metrics":[{"other":{"type":"ssvc","content":{"timestamp":"2026-09-11T16:48:36.016068Z","id":"CVE-2026-88047","options":[{"Exploitation":"none"},{"Automatable":"no"},{"Technical Impact":"total"}],"role":"CISA Coordinator","version":"2.0.3"}}}],"title":"CISA ADP Vulnrichment","providerMetadata":{"orgId":"134c704f-9b21-4f2e-91b3-4a467353bcc0","shortName":"CISA-ADP","dateUpdated":"2026-09-11T20:33:10.471Z"}}]}}