nday
CVE-2024-34359 GHSA-56xg-wfcc-g829

llama-cpp-python vulnerable to Remote Code Execution by Server-Side Template Injection in Model Metadata

abetlen / llama-cpp-python

披露后第 920 天有补丁记录。已有补丁记录,修复版本是 llama-cpp-python 0.2.72。四个 PoC 来源都还没有收录。尚未列入 CISA KEV。

标签 攻击途径网络无需认证 软件包生态PyPI
这些标签的依据

这些标签由 nday 按固定规则从下列事实自动推导,不是 NVD、编号分配方或其他来源给出的。全部标签和规则见 ~/tags。

网络
编号分配方 GitHub_M 给出的 CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H(CVSS 3.1)中的 AV:N
无需认证
编号分配方 GitHub_M 给出的 CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H(CVSS 3.1)中的 PR:N
PyPI
GHSA-56xg-wfcc-g829:pip 包 llama-cpp-python
当前阶段
PAT
披露
披露到补丁
T+920d
CVSS
9.7 CRITICAL v3.1

生命周期

横轴 UTC;点=精确到分钟,宽条=仅日期,空心=未知或推定。
时间未知
DIS披露
2024-05-10T17:07Z
PAT补丁
2026-11-16T16:00Z
ANA分析
尚无记录
POCPoC
尚无记录
ITW在野
尚无记录
KEVKEV
尚无记录

摘要

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.

以上是 CVE 记录(cvelist)中的原文,未经改写。

利用条件

按 CVSS 向量说明攻击需要的条件。
攻击途径 AV:N
网络:攻击者只要能通过网络访问到目标即可
攻击复杂度 AC:L
低:不依赖特殊条件,攻击者可预期重复成功
所需权限 PR:N
无:不需要账号或授权
用户交互 UI:R
需要:须有用户执行某个操作,例如打开文件或点击链接

CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H

CVSS 3.1 向量,来自 CVE 记录,由 CNA GitHub_M 评定。

事件记录

+DIS披露

CVE 记录发布,编号分配方是 GitHub_M。CVSS 9.7,严重。CISA 的 SSVC 评估中利用状态为 poc。

来源 cvelist · 本站 批量导入 · 原始记录
{
  "id": 333071,
  "type": "disclosed",
  "source": "cvelist",
  "url": "https://www.cve.org/CVERecord?id=CVE-2024-34359",
  "occurred_at": "2024-05-10T17:07:18.85Z",
  "observed_at": "2026-11-13T05:38:34.075966Z",
  "is_backfill": true,
  "dedupe_key": "",
  "detail": {
    "cvss": {
      "source": "cna",
      "vector": "CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H",
      "version": "3.1",
      "base_score": 9.7,
      "base_severity": "CRITICAL"
    },
    "ssvc": {
      "timestamp": "2024-05-15T19:35:24.408358Z",
      "automatable": "no",
      "exploitation": "poc",
      "technical_impact": "total"
    },
    "state": "PUBLISHED",
    "date_published": "2024-05-10T17:07:18.850Z",
    "assigner_short_name": "GitHub_M"
  }
}
来源未给时间,本站实时观测
+PAT补丁发布

公告给出修复版本 llama-cpp-python 0.2.72。公告附有修复提交。公告本身发布于 ,补丁实际发布时间没有记录。

来源 ghsa GHSA-56xg-wfcc-g829 · 本站 实时观测 · 原始记录
{
  "id": 472942,
  "type": "patch_released",
  "source": "ghsa",
  "url": "https://github.com/advisories/GHSA-56xg-wfcc-g829",
  "occurred_at": null,
  "observed_at": "2026-11-16T16:00:12.562502Z",
  "is_backfill": false,
  "dedupe_key": "GHSA-56xg-wfcc-g829",
  "detail": {
    "cvss": {
      "cvss_v3": {
        "score": 9.6,
        "vector_string": "CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H"
      },
      "cvss_v4": {
        "score": 0.0,
        "vector_string": null
      }
    },
    "cwes": [
      {
        "name": "Improper Neutralization of Equivalent Special Elements",
        "cwe_id": "CWE-76"
      }
    ],
    "ghsa_id": "GHSA-56xg-wfcc-g829",
    "packages": [
      {
        "name": "llama-cpp-python",
        "ecosystem": "pip",
        "first_patched_version": "0.2.72",
        "vulnerable_version_range": ">= 0.2.30, <= 0.2.71"
      }
    ],
    "severity": "critical",
    "references": [
      "https://github.com/abetlen/llama-cpp-python/security/advisories/GHSA-56xg-wfcc-g829",
      "https://nvd.nist.gov/vuln/detail/CVE-2024-34359",
      "https://github.com/abetlen/llama-cpp-python/commit/b454f40a9a1787b2b5659cd2cb00819d983185df",
      "https://github.com/pypa/advisory-database/tree/main/vulns/llama-cpp-python/PYSEC-2026-392.yaml",
      "https://pypi.org/project/llama-cpp-python",
      "https://github.com/advisories/GHSA-56xg-wfcc-g829"
    ],
    "fix_commit_urls": [
      "https://github.com/abetlen/llama-cpp-python/commit/b454f40a9a1787b2b5659cd2cb00819d983185df"
    ],
    "github_reviewed_at": "2024-05-13T14:10:18Z",
    "advisory_updated_at": "2026-11-16T15:19:29Z",
    "source_code_location": "https://github.com/abetlen/llama-cpp-python",
    "advisory_published_at": "2024-05-13T14:10:18Z"
  }
}

纠错

报告错误或缺失

页面有误或缺失?告诉编辑;采纳后在本页修订记录公开说明,上游数据不会被改动。

研究员讨论

近 7 天有 0 位研究员提到

研究员在 X 上提到此 CVE 的帖子,原文照录,nday 不核实。

尚未采集到名单内研究员在 X 上提到此 CVE 的帖子。

讨论

0 条评论

还没有评论。