CVE-2024-34359llama-cpp-python vulnerable to Remote Code Execution by Server-Side Template Injection in Model Metadata
- 9.7CriticalCVSS base score
- 26.0%Exploitation in 30 daysEPSS · top 2.0% of all CVEs
- NoKnown exploitednot in CISA's KEV catalog
- YesPublic exploitsa reference or SSVC says so
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.
Public exploit
An exploit or proof of concept is public: anyone can try it against an unpatched system. CISA's SSVC rates its exploitation: a proof of concept is public.
Timeline
ID reserved
By GitHub_M
- 8 days later
· 8 days later
Published
- 3 months later
· 3 months later
Record updated
Changes after publication (a new score, a public exploit, EPSS crossing 1, 10 or 50 %, leaving KEV) are kept since November 2026; earlier ones are not known.
Scores
| Scored by | CVSS | Score | Vector |
|---|---|---|---|
| GitHub_MCNA (assigner) | 3.1 | Critical9.7 | CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H |
| NVDNVD · Deferred | 3.1 | Critical9.6 | CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H |
- EPSS (exploitation in 30 days)
- 26.0% · top 2.0% of all CVEs (14 Nov 2026)
- CISA SSVC
- Exploitation: poc · Automatable: no · Technical impact: total
The list uses the assigner's score when there is one, then CISA's, then NVD's: Critical 9.7.
Affected products
- affected >= 0.2.30, <= 0.2.71
Affected packages
From reviewed advisories of the GitHub Advisory Database.
- PyPIllama-cpp-pythonGHSA-56xg-wfcc-g829 (opens in a new tab)
References
References2
- https://github.com/abetlen/llama-cpp-python/security/advisories/GHSA-56xg-wfcc-g829 (opens in a new tab)x_refsource_CONFIRMx_transferred
- https://github.com/abetlen/llama-cpp-python/commit/b454f40a9a1787b2b5659cd2cb00819d983185df (opens in a new tab)x_refsource_MISCx_transferred
Sources
The same CVE in the primary databases and aggregators, to check against.
- CVE.org record (opens in a new tab)
- CVE List JSON (GitHub) (opens in a new tab)
- NVD (opens in a new tab)
- FIRST EPSS (opens in a new tab)
- EUVD EUVD-2024-1433 (opens in a new tab)
- OSV.dev (opens in a new tab)
- GitHub Advisory GHSA-56xg-wfcc-g829 (opens in a new tab)
- CIRCL Vulnerability-Lookup (opens in a new tab)
Badge for a README or a ticket
[](https://cveledger.app/cve/CVE-2024-34359)Record last updated .