AVID-2026-R1520

Description

llama.cpp allows Arbitrary Address Read in rpc_server::get_tensor (CVE-2024-42478)

Details

llama.cpp provides LLM inference in C/C++. The unsafe data pointer member in the rpc_tensor structure can cause arbitrary address reading. This vulnerability is fixed in b3561.

Reason for inclusion in AVID: The CVE targets llama.cpp, a general-purpose AI inference library used in ML pipelines. It describes an out-of-bounds read vulnerability in a component (rpc_tensor) of llama.cpp that can be exploited remotely, which is a software vulnerability affecting AI software stacks used to build/serve AI models. The issue is in a software dependency/component relevant to AI systems, and there are references and a fix commit, providing sufficient evidence.

References

• NVD entry
• https://github.com/ggerganov/llama.cpp/security/advisories/GHSA-5vm9-p64x-gqw9
• https://github.com/ggerganov/llama.cpp/commit/b72942fac998672a79a1ae3c03b340f7e629980b

Affected or Relevant Artifacts

• Developer: Meta
• Deployer: ggerganov
• Artifact Details:

Impact

AVID Taxonomy Categorization

• Risk domains: Security
• SEP subcategories: S0100: Software Vulnerability
• Lifecycle stages: L06: Deployment

CVSS

CWE

Other information

• Report Type: Advisory
• Credits:
• Date Reported: 2024-08-12
• Version: 0.3.3
• AVID Entry