Code execution via unsandboxed GGUF chat templates
Published Jul 2, 2024 · Updated Aug 1, 2024
Code injection in ParisNeo LoLLMs WebUI allows attackers to execute code by loading a malicious GGUF model through bindings_zoo. The Llama constructor passes the model metadata's chat template to Jinja2ChatFormatter, which renders it with an unsandboxed Jinja2 environment. Exploitation requires loading and interacting with a crafted model; injected code runs with the LoLLMs process privileges.
Summary
What happened
Code injection in ParisNeo LoLLMs WebUI allows attackers to execute code by loading a malicious GGUF model through bindings_zoo. The Llama constructor passes the model metadata's chat template to Jinja2ChatFormatter, which renders it with an unsandboxed Jinja2 environment. Exploitation requires loading and interacting with a crafted model; injected code runs with the LoLLMs process privileges.
The record
- CVE
- CVE-2024-4897
- Published
- Jul 2, 2024
- Updated
- Aug 1, 2024
- Vendor
- ParisNeo
- Product
- LoLLMs WebUI
- Classifications
- CWE-76, T1203
- Attack vector
- local
- Privileges
- unauthenticated
Timeline
How it unfolded
- Jul 2, 2024CVE publishedPublication date reported by the CVE source.
- Aug 1, 2024Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
Compare these published version ranges with your installed build and any vendor patches.
- Affected versionversion=9.5
- Affected versionversion=unspecified <=latest
What conditions does exploitation require?
What is affected?
Published CVSS scores
CVSS describes severity. EPSS estimates exploitation probability.
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Weakness, pattern, technique
Public exploit references
No public exploit references are available in this record.
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo