{
    "id": "CVE-2024-34359",
    "published": "2024-05-14 15:38:45",
    "last_modified": "2026-06-17 07:33:14",
    "cvss_score": "9.6",
    "cvss_severity": "CRITICAL",
    "cvss_version": "3.1",
    "cvss_vector": "CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H",
    "cwe": "CWE-76",
    "description": "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.",
    "epss_score": "0.26001",
    "epss_percentile": "0.97933",
    "kev": 0,
    "kev_due": null,
    "has_exploit": 0,
    "updated_at": "2026-10-03 18:17:44",
    "priority": {
        "rank": 2,
        "label": "Patch early",
        "why": "EPSS 26% — above the 10% action threshold."
    },
    "products": [],
    "kev_detail": null,
    "exploits": [],
    "refs_list": [
        "https://github.com/abetlen/llama-cpp-python/commit/b454f40a9a1787b2b5659cd2cb00819d983185df",
        "https://github.com/abetlen/llama-cpp-python/security/advisories/GHSA-56xg-wfcc-g829",
        "https://github.com/abetlen/llama-cpp-python/commit/b454f40a9a1787b2b5659cd2cb00819d983185df",
        "https://github.com/abetlen/llama-cpp-python/security/advisories/GHSA-56xg-wfcc-g829"
    ]
}