{"dataType": "CVE_RECORD", "dataVersion": "5.1", "cveMetadata": {"cveId": "CVE-2025-49847", "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa", "state": "PUBLISHED", "assignerShortName": "GitHub_M", "dateReserved": "2025-06-11T14:33:57.800Z", "datePublished": "2025-06-17T20:04:40.893Z", "dateUpdated": "2025-06-18T13:41:11.407Z"}, "containers": {"cna": {"title": "llama.cpp Vulnerable to Buffer Overflow via Malicious GGUF Model", "problemTypes": [{"descriptions": [{"cweId": "CWE-119", "lang": "en", "description": "CWE-119: Improper Restriction of Operations within the Bounds of a Memory Buffer", "type": "CWE"}]}, {"descriptions": [{"cweId": "CWE-195", "lang": "en", "description": "CWE-195: Signed to Unsigned Conversion Error", "type": "CWE"}]}], "metrics": [{"cvssV3_1": {"attackComplexity": "LOW", "attackVector": "NETWORK", "availabilityImpact": "HIGH", "baseScore": 8.8, "baseSeverity": "HIGH", "confidentialityImpact": "HIGH", "integrityImpact": "HIGH", "privilegesRequired": "NONE", "scope": "UNCHANGED", "userInteraction": "REQUIRED", "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H", "version": "3.1"}}], "references": [{"name": "https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-8wwf-w4qm-gpqr", "tags": ["x_refsource_CONFIRM"], "url": "https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-8wwf-w4qm-gpqr"}, {"name": "https://github.com/ggml-org/llama.cpp/commit/3cfbbdb44e08fd19429fed6cc85b982a91f0efd5", "tags": ["x_refsource_MISC"], "url": "https://github.com/ggml-org/llama.cpp/commit/3cfbbdb44e08fd19429fed6cc85b982a91f0efd5"}], "affected": [{"vendor": "ggml-org", "product": "llama.cpp", "versions": [{"version": "< b5662", "status": "affected"}]}], "providerMetadata": {"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa", "shortName": "GitHub_M", "dateUpdated": "2025-06-17T20:04:40.893Z"}, "descriptions": [{"lang": "en", "value": "llama.cpp is an inference of several LLM models in C/C++. Prior to version b5662, an attacker\u2010supplied GGUF model vocabulary can trigger a buffer overflow in llama.cpp\u2019s vocabulary\u2010loading code. Specifically, the helper _try_copy in llama.cpp/src/vocab.cpp: llama_vocab::impl::token_to_piece() casts a very large size_t token length into an int32_t, causing the length check (if (length < (int32_t)size)) to be bypassed. As a result, memcpy is still called with that oversized size, letting a malicious model overwrite memory beyond the intended buffer. This can lead to arbitrary memory corruption and potential code execution. This issue has been patched in version b5662."}], "source": {"advisory": "GHSA-8wwf-w4qm-gpqr", "discovery": "UNKNOWN"}}, "adp": [{"metrics": [{"other": {"type": "ssvc", "content": {"timestamp": "2025-06-18T13:40:43.172535Z", "id": "CVE-2025-49847", "options": [{"Exploitation": "poc"}, {"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": "2025-06-18T13:41:11.407Z"}}]}}

{"dataType": "CVE_RECORD", "containers": {"adp": [{"title": "CISA ADP Vulnrichment", "metrics": [{"other": {"type": "ssvc", "content": {"id": "CVE-2025-49847", "role": "CISA Coordinator", "options": [{"Exploitation": "poc"}, {"Automatable": "no"}, {"Technical Impact": "total"}], "version": "2.0.3", "timestamp": "2025-06-18T13:40:43.172535Z"}}}], "providerMetadata": {"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "shortName": "CISA-ADP", "dateUpdated": "2025-06-18T13:40:46.678Z"}}], "cna": {"title": "llama.cpp Vulnerable to Buffer Overflow via Malicious GGUF Model", "source": {"advisory": "GHSA-8wwf-w4qm-gpqr", "discovery": "UNKNOWN"}, "metrics": [{"cvssV3_1": {"scope": "UNCHANGED", "version": "3.1", "baseScore": 8.8, "attackVector": "NETWORK", "baseSeverity": "HIGH", "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H", "integrityImpact": "HIGH", "userInteraction": "REQUIRED", "attackComplexity": "LOW", "availabilityImpact": "HIGH", "privilegesRequired": "NONE", "confidentialityImpact": "HIGH"}}], "affected": [{"vendor": "ggml-org", "product": "llama.cpp", "versions": [{"status": "affected", "version": "< b5662"}]}], "references": [{"url": "https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-8wwf-w4qm-gpqr", "name": "https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-8wwf-w4qm-gpqr", "tags": ["x_refsource_CONFIRM"]}, {"url": "https://github.com/ggml-org/llama.cpp/commit/3cfbbdb44e08fd19429fed6cc85b982a91f0efd5", "name": "https://github.com/ggml-org/llama.cpp/commit/3cfbbdb44e08fd19429fed6cc85b982a91f0efd5", "tags": ["x_refsource_MISC"]}], "descriptions": [{"lang": "en", "value": "llama.cpp is an inference of several LLM models in C/C++. Prior to version b5662, an attacker\u2010supplied GGUF model vocabulary can trigger a buffer overflow in llama.cpp\u2019s vocabulary\u2010loading code. Specifically, the helper _try_copy in llama.cpp/src/vocab.cpp: llama_vocab::impl::token_to_piece() casts a very large size_t token length into an int32_t, causing the length check (if (length < (int32_t)size)) to be bypassed. As a result, memcpy is still called with that oversized size, letting a malicious model overwrite memory beyond the intended buffer. This can lead to arbitrary memory corruption and potential code execution. This issue has been patched in version b5662."}], "problemTypes": [{"descriptions": [{"lang": "en", "type": "CWE", "cweId": "CWE-119", "description": "CWE-119: Improper Restriction of Operations within the Bounds of a Memory Buffer"}]}, {"descriptions": [{"lang": "en", "type": "CWE", "cweId": "CWE-195", "description": "CWE-195: Signed to Unsigned Conversion Error"}]}], "providerMetadata": {"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa", "shortName": "GitHub_M", "dateUpdated": "2025-06-17T20:04:40.893Z"}}}, "cveMetadata": {"cveId": "CVE-2025-49847", "state": "PUBLISHED", "dateUpdated": "2025-06-18T13:41:11.407Z", "dateReserved": "2025-06-11T14:33:57.800Z", "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa", "datePublished": "2025-06-17T20:04:40.893Z", "assignerShortName": "GitHub_M"}, "dataVersion": "5.1"}

{"cveTags": [], "descriptions": [{"lang": "en", "value": "llama.cpp is an inference of several LLM models in C/C++. Prior to version b5662, an attacker\u2010supplied GGUF model vocabulary can trigger a buffer overflow in llama.cpp\u2019s vocabulary\u2010loading code. Specifically, the helper _try_copy in llama.cpp/src/vocab.cpp: llama_vocab::impl::token_to_piece() casts a very large size_t token length into an int32_t, causing the length check (if (length < (int32_t)size)) to be bypassed. As a result, memcpy is still called with that oversized size, letting a malicious model overwrite memory beyond the intended buffer. This can lead to arbitrary memory corruption and potential code execution. This issue has been patched in version b5662."}], "id": "CVE-2025-49847", "lastModified": "2025-06-17T20:50:23.507", "metrics": {"cvssMetricV31": [{"cvssData": {"attackComplexity": "LOW", "attackVector": "NETWORK", "availabilityImpact": "HIGH", "baseScore": 8.8, "baseSeverity": "HIGH", "confidentialityImpact": "HIGH", "integrityImpact": "HIGH", "privilegesRequired": "NONE", "scope": "UNCHANGED", "userInteraction": "REQUIRED", "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H", "version": "3.1"}, "exploitabilityScore": 2.8, "impactScore": 5.9, "source": "security-advisories@github.com", "type": "Secondary"}]}, "published": "2025-06-17T20:15:32.437", "references": [{"source": "security-advisories@github.com", "url": "https://github.com/ggml-org/llama.cpp/commit/3cfbbdb44e08fd19429fed6cc85b982a91f0efd5"}, {"source": "security-advisories@github.com", "url": "https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-8wwf-w4qm-gpqr"}], "sourceIdentifier": "security-advisories@github.com", "vulnStatus": "Awaiting Analysis", "weaknesses": [{"description": [{"lang": "en", "value": "CWE-119"}, {"lang": "en", "value": "CWE-195"}], "source": "security-advisories@github.com", "type": "Primary"}]}

{}