{
  "containers": {
    "cna": {
      "affected": [
        {
          "product": "tesseract",
          "vendor": "tesseract-ocr",
          "versions": [
            {
              "status": "affected",
              "version": "\u003c= 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",
  "vulnerability-lookup:meta": {
    "nvd": "{\"cve\":{\"id\":\"CVE-2026-88052\",\"sourceIdentifier\":\"security-advisories@github.com\",\"published\":\"2026-09-10T18:18:14.317\",\"lastModified\":\"2026-09-10T19:54:25.810\",\"vulnStatus\":\"Awaiting Analysis\",\"cveTags\":[],\"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\":[{\"source\":\"security-advisories@github.com\",\"affectedData\":[{\"vendor\":\"tesseract-ocr\",\"product\":\"tesseract\",\"versions\":[{\"version\":\"\u003c= 5.5.3\",\"status\":\"affected\"}]}]}],\"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}]},\"weaknesses\":[{\"source\":\"security-advisories@github.com\",\"type\":\"Primary\",\"description\":[{\"lang\":\"en\",\"value\":\"CWE-129\"},{\"lang\":\"en\",\"value\":\"CWE-787\"}]}],\"references\":[{\"url\":\"https://github.com/tesseract-ocr/tesseract/commit/2d04d640db2e8c7e3bab2369d599343b5a8b8443\",\"source\":\"security-advisories@github.com\"},{\"url\":\"https://github.com/tesseract-ocr/tesseract/security/advisories/GHSA-2hm8-q5c7-c373\",\"source\":\"security-advisories@github.com\"}]}}"
  }
}