AVID-2026-R1417
Description
Vulnerability CVE-2024-21802
Details
A heap-based buffer overflow vulnerability exists in the GGUF library info->ne functionality of llama.cpp Commit 18c2e17. A specially crafted .gguf file can lead to code execution. An attacker can provide a malicious file to trigger this vulnerability.
Reason for inclusion in AVID: The CVE describes a heap-based buffer overflow in the GGUF handling of llama.cpp that can lead to code execution via a crafted .gguf file. This is a software vulnerability in a component (llama.cpp) used to load/infer AI models, affecting AI model loading/execution pipelines. It concerns software used to build/deploy/run AI systems (libraries, runtimes, artifact ecosystems) rather than hardware/firmware, thus relevant to the AI supply chain. The report provides explicit signals (CVE-2024-21802, CVSS 3.1 HIGH, references to NVD/Talos) that establish vulnerability and impact.
References
Affected or Relevant Artifacts
- Developer: Meta
- Deployer: llama.cpp
- Artifact Details:
| Type | Name |
|---|---|
| System | llama.cpp |
Impact
AVID Taxonomy Categorization
- Risk domains: Security
- SEP subcategories: S0100: Software Vulnerability
- Lifecycle stages: L06: Deployment
CVSS
| Version | 3.1 |
| Vector String | CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H |
| Base Score | 8.8 |
| Base Severity | 🔴 High |
| Attack Vector | NETWORK |
| Attack Complexity | 🟢 Low |
| Privileges Required | NONE |
| User Interaction | REQUIRED |
| Scope | UNCHANGED |
| Confidentiality Impact | 🔴 High |
| Integrity Impact | 🔴 High |
| Availability Impact | 🔴 High |
CWE
| ID | Description |
|---|---|
| CWE-122 | CWE-122: Heap-based Buffer Overflow |
Other information
- Report Type: Advisory
- Credits:
- Date Reported: 2024-02-26
- Version: 0.3.3
- AVID Entry