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.
| Métrique | Valeur | Interprétation |
|---|---|---|
|
AV (Vecteur d'Attaque)
Attack Vector
|
Network (N)
|
Exploit possible à distance via réseau (HTTP, API, etc.) |
|
AC (Complexité d'Attaque)
Attack Complexity
|
Low (L)
|
Peu de conditions requises pour exploiter |
|
PR (Privilèges Requis)
Privileges Required
|
None (N)
|
Aucune authentification requise |
|
UI (Interaction Utilisateur)
User Interaction
|
Required (R)
|
Nécessite une action utilisateur (clic lien, ouverture fichier, etc.) |
|
S (Périmètre)
Scope
|
Changed (C)
|
Impact s'étend au-delà du composant compromis |
|
C (Impact Confidentialité)
Confidentiality Impact
|
High (H)
|
Divulgation totale d'informations |
|
I (Impact Intégrité)
Integrity Impact
|
High (H)
|
Modification totale des données possible |
|
A (Impact Disponibilité)
Availability Impact
|
High (H)
|
Interruption totale du service possible |
llama-cpp-python vulnerable to Remote Code Execution by Server-Side Template Injection in Model Metadata
llama-cpp-python vulnerable to Remote Code Execution by Server-Side Template Injection in Model Metadata