llama-cpp-python vulnerable to Remote Code Execution by Server-Side Template Injection in Model Metadata
CVE-2024-34359 · GHSA-56xg-wfcc-g829 · published 2024-05-13 · updated 2026-11-16
- Severity
- Critical
- CVSS score
- 9.6
- Chance of exploitation (EPSS)
- 26.0%
- Fixed in
- 0.2.72
- Exploitation Public proof of concept
- Automatable No
- Technical impact Total
- CISA SSVC
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 Server Side Template Injection which leads to RCE by a carefully constructed payload.
Upgrade llama-cpp-python to 0.2.72 or later.
| Package | Registry | Affected | Fixed in |
|---|---|---|---|
| llama-cpp-python | PyPI | >= 0.2.30, <= 0.2.71 | 0.2.72 |
- CriticalLiteLLM has SQL Injection in Proxy API key verificationlitellmExploited
- Criticaln8n Vulnerable to Remote Code Execution via Expression Injectionn8n, n8nExploited
- HighLiteLLM has a sandbox escape in custom-code guardraillitellmExploited
- HighLangflow affected by Remote Code Execution via validate_code() exec()langflowExploited
- CriticalJupyter MCP Server: Browser DNS rebinding can hijack the Jupyter backend through management routesjupyter-mcp-server
- Criticalmem0ai Databricks vector store vulnerable to SQL injectionmem0ai
The impact, patch and workaround text comes from the advisory, shortened (GitHub Advisory Database, CC BY 4.0). Proof-of-concept and reproduction sections and code are left out; the original advisory has them.