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

## Description `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 RCE by a carefully constructed payload. ## Source-to-Sink ### `llama.py` -> `class Llama` -> `__init__`: ```python class Llama: """High-level Python wrapper for a llama.cpp model.""" __backend_initialized = False def __init__( self, model_path: str, # lots of params; Ignoring ): self.verbose = verbose set_verbose(verbose) if not Llama.__backend_initialized: with suppress_stdout_stderr(disable=verbose): llama_cpp.llama_backend_init() Llama.__backend_initialized = True # Ignoring lines of unrelated codes..... try: self.metadata = self._model.metadata() except Exception as e: self.metadata = {} if self.verbose: print(f"Failed to load metadata: {e}", file=sys.stderr) if self.verbose: print(f"Model metadata: {self.metadata}", file=sys.stderr) if ( self.chat_format is None and self.chat_handler is None and "tokenizer.chat_template" in self.metadata ): chat_format = llama_chat_format.guess_chat_format_from_gguf_metadata( self.metadata ) if chat_format is not None: self.chat_format = chat_format if self.verbose: print(f"Guessed chat format: {chat_format}", file=sys.stderr) else: template = self.metadata["tokenizer.chat_template"] try: eos_token_id = int(self.metadata["tokenizer.ggml.eos_token_id"]) except: eos_token_id = self.token_eos() try: bos_token_id = int(self.metadata["tokenizer.ggml.bos_token_id"]) except: bos_token_id = self.token_bos() eos_token = self._model.token_get_text(eos_token_id) bos_token = self._model.token_get_text(bos_token_id) if self.verbose: print(f"Using gguf chat template: {template}", file=sys.stderr) print(f"Using chat eos_token: {eos_token}", file=sys.stderr) print(f"Using chat bos_token: {bos_token}", file=sys.stderr) self.chat_handler = llama_chat_format.Jinja2ChatFormatter( template=template, eos_token=eos_token, bos_token=bos_token, stop_token_ids=[eos_token_id], ).to_chat_handler() if self.chat_format is None and self.chat_handler is None: self.chat_format = "llama-2" if self.verbose: print(f"Using fallback chat format: {chat_format}", file=sys.stderr) ``` In `llama.py`, `llama-cpp-python` defined the fundamental class for model initialization parsing (Including `NUMA, LoRa settings`, `loading tokenizers,` and stuff ). In our case, we will be focusing on the parts where it processes `metadata`; it first checks if `chat_format` and `chat_handler` are `None` and checks if the key `tok

CVSS 3.1

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

Severity from

GitHub (reviewed advisory)

Weakness

CWE-76

Also known as

CVE-2024-34359, PYSEC-2026-392

• github.com/abetlen/llama-cpp-python/security/advisories/GHSA-56xg-wfcc-g829
• nvd.nist.gov/vuln/detail/CVE-2024-34359
• github.com/abetlen/llama-cpp-python/commit/b454f40a9a1787b2b5659cd2cb00819d983185df
• github.com/abetlen/llama-cpp-python