{"dataType": "CVE_RECORD", "dataVersion": "5.1", "cveMetadata": {"cveId": "CVE-2024-34359", "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa", "state": "PUBLISHED", "assignerShortName": "GitHub_M", "dateReserved": "2024-05-02T06:36:32.439Z", "datePublished": "2024-05-10T17:07:18.850Z", "dateUpdated": "2024-06-06T18:29:15.313Z"}, "containers": {"cna": {"title": "llama-cpp-python vulnerable to Remote Code Execution by Server-Side Template Injection in Model Metadata", "problemTypes": [{"descriptions": [{"cweId": "CWE-76", "lang": "en", "description": "CWE-76: Improper Neutralization of Equivalent Special Elements", "type": "CWE"}]}], "metrics": [{"cvssV3_1": {"attackComplexity": "LOW", "attackVector": "NETWORK", "availabilityImpact": "HIGH", "baseScore": 9.7, "baseSeverity": "CRITICAL", "confidentialityImpact": "HIGH", "integrityImpact": "HIGH", "privilegesRequired": "NONE", "scope": "CHANGED", "userInteraction": "REQUIRED", "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H", "version": "3.1"}}], "references": [{"name": "https://github.com/abetlen/llama-cpp-python/security/advisories/GHSA-56xg-wfcc-g829", "tags": ["x_refsource_CONFIRM"], "url": "https://github.com/abetlen/llama-cpp-python/security/advisories/GHSA-56xg-wfcc-g829"}, {"name": "https://github.com/abetlen/llama-cpp-python/commit/b454f40a9a1787b2b5659cd2cb00819d983185df", "tags": ["x_refsource_MISC"], "url": "https://github.com/abetlen/llama-cpp-python/commit/b454f40a9a1787b2b5659cd2cb00819d983185df"}], "affected": [{"vendor": "abetlen", "product": "llama-cpp-python", "versions": [{"version": ">= 0.2.30, <= 0.2.71", "status": "affected"}]}], "providerMetadata": {"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa", "shortName": "GitHub_M", "dateUpdated": "2024-05-10T17:07:18.850Z"}, "descriptions": [{"lang": "en", "value": "llama-cpp-python is the Python bindings for llama.cpp. `llama-cpp-python` depends on class `Llama` in `llama.py` to load `.gguf` llama.cpp or Latency Machine Learning Models. The `__init__` constructor built in the `Llama` takes several parameters to configure the loading and running of the model. Other than `NUMA, LoRa settings`, `loading tokenizers,` and `hardware settings`, `__init__` also loads the `chat template` from targeted `.gguf` 's Metadata and furtherly parses it to `llama_chat_format.Jinja2ChatFormatter.to_chat_handler()` to construct the `self.chat_handler` for this model. Nevertheless, `Jinja2ChatFormatter` parse the `chat template` within the Metadate with sandbox-less `jinja2.Environment`, which is furthermore rendered in `__call__` to construct the `prompt` of interaction. This allows `jinja2` Server Side Template Injection which leads to remote code execution by a carefully constructed payload."}], "source": {"advisory": "GHSA-56xg-wfcc-g829", "discovery": "UNKNOWN"}}, "adp": [{"affected": [{"vendor": "abetlen", "product": "llama-cpp-python", "cpes": ["cpe:2.3:a:abetlen:llama-cpp-python:*:*:*:*:*:*:*:*"], "defaultStatus": "unknown", "versions": [{"version": "0.2.30", "status": "affected", "lessThanOrEqual": "0.2.71", "versionType": "custom"}]}], "metrics": [{"other": {"type": "ssvc", "content": {"timestamp": "2024-05-15T19:35:24.408358Z", "id": "CVE-2024-34359", "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": "2024-06-06T18:29:15.313Z"}}]}}

{"descriptions": [{"lang": "en", "value": "llama-cpp-python is the Python bindings for llama.cpp. `llama-cpp-python` depends on class `Llama` in `llama.py` to load `.gguf` llama.cpp or Latency Machine Learning Models. The `__init__` constructor built in the `Llama` takes several parameters to configure the loading and running of the model. Other than `NUMA, LoRa settings`, `loading tokenizers,` and `hardware settings`, `__init__` also loads the `chat template` from targeted `.gguf` 's Metadata and furtherly parses it to `llama_chat_format.Jinja2ChatFormatter.to_chat_handler()` to construct the `self.chat_handler` for this model. Nevertheless, `Jinja2ChatFormatter` parse the `chat template` within the Metadate with sandbox-less `jinja2.Environment`, which is furthermore rendered in `__call__` to construct the `prompt` of interaction. This allows `jinja2` Server Side Template Injection which leads to remote code execution by a carefully constructed payload."}], "id": "CVE-2024-34359", "lastModified": "2024-05-14T16:12:23.490", "metrics": {"cvssMetricV31": [{"cvssData": {"attackComplexity": "LOW", "attackVector": "NETWORK", "availabilityImpact": "HIGH", "baseScore": 9.6, "baseSeverity": "CRITICAL", "confidentialityImpact": "HIGH", "integrityImpact": "HIGH", "privilegesRequired": "NONE", "scope": "CHANGED", "userInteraction": "REQUIRED", "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H", "version": "3.1"}, "exploitabilityScore": 2.8, "impactScore": 6.0, "source": "security-advisories@github.com", "type": "Secondary"}]}, "published": "2024-05-14T15:38:45.093", "references": [{"source": "security-advisories@github.com", "url": "https://github.com/abetlen/llama-cpp-python/commit/b454f40a9a1787b2b5659cd2cb00819d983185df"}, {"source": "security-advisories@github.com", "url": "https://github.com/abetlen/llama-cpp-python/security/advisories/GHSA-56xg-wfcc-g829"}], "sourceIdentifier": "security-advisories@github.com", "vulnStatus": "Awaiting Analysis", "weaknesses": [{"description": [{"lang": "en", "value": "CWE-76"}], "source": "security-advisories@github.com", "type": "Secondary"}]}

{}