{"api_version":"1","generated_at":"2026-11-10T11:26:08+00:00","cve":"CVE-2026-115878","urls":{"html":"https://cve.report/CVE-2026-115878","api":"https://cve.report/api/cve/CVE-2026-115878.json","docs":"https://cve.report/api","cve_org":"https://www.cve.org/CVERecord?id=CVE-2026-115878","nvd":"https://nvd.nist.gov/vuln/detail/CVE-2026-115878"},"summary":{"title":"Stanza: RCE via pickle deserialization in the lemmatizer","description":"Stanza is a Stanford NLP Python library for tokenization, sentence segmentation, NER, and parsing of many human languages. From 1.14.0 until 1.15.0, loading an attacker-supplied lemmatizer checkpoint can execute arbitrary code because stanza/models/lemma/trainer.py stores pos_dict as gzip-compressed pickle bytes and Trainer.load passes the decompressed stream to unrestricted pickle.loads. The outer torch.load call uses weights_only=True, but the nested bytes are treated as a primitive and are not inspected by that allowlist. The path is reachable during pipeline construction through a caller-influenced lemma_model_path, before inference begins. This issue is fixed in version 1.15.0.","state":"PUBLISHED","assigner":"GitHub_M","published_at":"2026-11-03 21:17:02","updated_at":"2026-11-03 23:17:30"},"problem_types":["CWE-94","CWE-502","CWE-94 CWE-94: Improper Control of Generation of Code ('Code Injection')","CWE-502 CWE-502: Deserialization of Untrusted Data"],"metrics":[{"version":"3.1","source":"security-advisories@github.com","type":"Secondary","score":"7.8","severity":"HIGH","vector":"CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H","data":{"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"}},{"version":"3.1","source":"CNA","type":"DECLARED","score":"7.8","severity":"HIGH","vector":"CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H","data":{"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"}}],"references":[{"url":"https://github.com/stanfordnlp/stanza/releases/tag/v1.15.0","name":"https://github.com/stanfordnlp/stanza/releases/tag/v1.15.0","refsource":"security-advisories@github.com","tags":[],"title":"","mime":"","httpstatus":"","archivestatus":"0"},{"url":"https://github.com/stanfordnlp/stanza/security/advisories/GHSA-gh9r-c94j-cmp5","name":"https://github.com/stanfordnlp/stanza/security/advisories/GHSA-gh9r-c94j-cmp5","refsource":"security-advisories@github.com","tags":[],"title":"","mime":"","httpstatus":"","archivestatus":"0"},{"url":"https://github.com/stanfordnlp/stanza/pull/1649","name":"https://github.com/stanfordnlp/stanza/pull/1649","refsource":"security-advisories@github.com","tags":[],"title":"","mime":"","httpstatus":"","archivestatus":"0"},{"url":"https://github.com/stanfordnlp/stanza/commit/b21e1c9b47b4fccff21d3b0a6c0687a19410c2f0","name":"https://github.com/stanfordnlp/stanza/commit/b21e1c9b47b4fccff21d3b0a6c0687a19410c2f0","refsource":"security-advisories@github.com","tags":[],"title":"","mime":"","httpstatus":"","archivestatus":"0"},{"url":"https://www.cve.org/CVERecord?id=CVE-2026-115878","name":"CVE Program record","refsource":"CVE.ORG","tags":["canonical"]},{"url":"https://nvd.nist.gov/vuln/detail/CVE-2026-115878","name":"NVD vulnerability detail","refsource":"NVD","tags":["canonical","analysis"]}],"affected":[{"source":"CNA","vendor":"stanfordnlp","product":"stanza","version":"affected = 1.14.0","platforms":[]}],"timeline":[],"solutions":[],"workarounds":[],"exploits":[],"credits":[],"nvd_cpes":[],"vendor_comments":[],"enrichments":{"kev":null,"epss":{"cve_year":"2026","cve_id":"115878","cve":"CVE-2026-115878","epss":"0.005970000","percentile":"0.487050000","score_date":"2026-11-04","updated_at":"2026-11-05 00:04:18"},"legacy_qids":[]},"source_records":{"cve_program":{"containers":{"adp":[{"metrics":[{"other":{"content":{"id":"CVE-2026-115878","options":[{"Exploitation":"none"},{"Automatable":"no"},{"Technical Impact":"total"}],"role":"CISA Coordinator","timestamp":"2026-11-03T22:36:42.446948Z","version":"2.0.3"},"type":"ssvc"}}],"providerMetadata":{"dateUpdated":"2026-11-03T22:39:36.547Z","orgId":"134c704f-9b21-4f2e-91b3-4a467353bcc0","shortName":"CISA-ADP"},"title":"CISA ADP Vulnrichment"}],"cna":{"affected":[{"product":"stanza","vendor":"stanfordnlp","versions":[{"status":"affected","version":"= 1.14.0"}]}],"descriptions":[{"lang":"en","value":"Stanza is a Stanford NLP Python library for tokenization, sentence segmentation, NER, and parsing of many human languages. From 1.14.0 until 1.15.0, loading an attacker-supplied lemmatizer checkpoint can execute arbitrary code because stanza/models/lemma/trainer.py stores pos_dict as gzip-compressed pickle bytes and Trainer.load passes the decompressed stream to unrestricted pickle.loads. The outer torch.load call uses weights_only=True, but the nested bytes are treated as a primitive and are not inspected by that allowlist. The path is reachable during pipeline construction through a caller-influenced lemma_model_path, before inference begins. This issue is fixed in version 1.15.0."}],"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-94","description":"CWE-94: Improper Control of Generation of Code ('Code Injection')","lang":"en","type":"CWE"}]},{"descriptions":[{"cweId":"CWE-502","description":"CWE-502: Deserialization of Untrusted Data","lang":"en","type":"CWE"}]}],"providerMetadata":{"dateUpdated":"2026-11-03T20:26:02.220Z","orgId":"a0819718-46f1-4df5-94e2-005712e83aaa","shortName":"GitHub_M"},"references":[{"name":"https://github.com/stanfordnlp/stanza/security/advisories/GHSA-gh9r-c94j-cmp5","tags":["x_refsource_CONFIRM"],"url":"https://github.com/stanfordnlp/stanza/security/advisories/GHSA-gh9r-c94j-cmp5"},{"name":"https://github.com/stanfordnlp/stanza/pull/1649","tags":["x_refsource_MISC"],"url":"https://github.com/stanfordnlp/stanza/pull/1649"},{"name":"https://github.com/stanfordnlp/stanza/commit/b21e1c9b47b4fccff21d3b0a6c0687a19410c2f0","tags":["x_refsource_MISC"],"url":"https://github.com/stanfordnlp/stanza/commit/b21e1c9b47b4fccff21d3b0a6c0687a19410c2f0"},{"name":"https://github.com/stanfordnlp/stanza/releases/tag/v1.15.0","tags":["x_refsource_MISC"],"url":"https://github.com/stanfordnlp/stanza/releases/tag/v1.15.0"}],"source":{"advisory":"GHSA-gh9r-c94j-cmp5","discovery":"UNKNOWN"},"title":"Stanza: RCE via pickle deserialization in the lemmatizer"}},"cveMetadata":{"assignerOrgId":"a0819718-46f1-4df5-94e2-005712e83aaa","assignerShortName":"GitHub_M","cveId":"CVE-2026-115878","datePublished":"2026-11-03T20:26:02.220Z","dateReserved":"2026-10-23T19:37:27.176Z","dateUpdated":"2026-11-03T22:39:36.547Z","state":"PUBLISHED"},"dataType":"CVE_RECORD","dataVersion":"5.2"},"nvd":{"publishedDate":"2026-11-03 21:17:02","lastModifiedDate":"2026-11-03 23:17:30","problem_types":["CWE-94","CWE-502","CWE-94 CWE-94: Improper Control of Generation of Code ('Code Injection')","CWE-502 CWE-502: Deserialization of Untrusted Data"],"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}],"ssvcV203":[{"source":"134c704f-9b21-4f2e-91b3-4a467353bcc0","ssvcData":{"timestamp":"2026-11-03T22:36:42.446948Z","id":"CVE-2026-115878","options":[{"exploitation":"none"},{"automatable":"no"},{"technicalImpact":"total"}],"role":"CISA Coordinator","version":"2.0.3"}}]},"configurations":[]},"legacy_mitre":{"record":{"CveYear":"2026","CveId":"115878","Ordinal":"1","Title":"Stanza: RCE via pickle deserialization in the lemmatizer","CVE":"CVE-2026-115878","Year":"2026"},"notes":[{"CveYear":"2026","CveId":"115878","Ordinal":"1","NoteData":"Stanza is a Stanford NLP Python library for tokenization, sentence segmentation, NER, and parsing of many human languages. From 1.14.0 until 1.15.0, loading an attacker-supplied lemmatizer checkpoint can execute arbitrary code because stanza/models/lemma/trainer.py stores pos_dict as gzip-compressed pickle bytes and Trainer.load passes the decompressed stream to unrestricted pickle.loads. The outer torch.load call uses weights_only=True, but the nested bytes are treated as a primitive and are not inspected by that allowlist. The path is reachable during pipeline construction through a caller-influenced lemma_model_path, before inference begins. This issue is fixed in version 1.15.0.","Type":"Description","Title":"Stanza: RCE via pickle deserialization in the lemmatizer"}]}}}