llama.cpp allows write-what-where in rpc_server::set_tensor
Summary
| CVE | CVE-2024-42479 |
|---|---|
| State | PUBLISHED |
| Assigner | GitHub_M |
| Source Priority | CVE Program / NVD first with legacy fallback |
| Published | 2024-08-12 15:15:21 UTC |
| Updated | 2026-04-27 17:44:53 UTC |
| Description | llama.cpp provides LLM inference in C/C++. The unsafe `data` pointer member in the `rpc_tensor` structure can cause arbitrary address writing. This vulnerability is fixed in b3561. |
Risk And Classification
Primary CVSS: v3.1 9.8 CRITICAL from [email protected]
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
EPSS: 0.056780000 probability, percentile 0.904140000 (date 2026-04-27)
Problem Types: CWE-123 | CWE-787 | CWE-123 CWE-123: Write-what-where Condition
| Version | Source | Type | Score | Severity | Vector |
|---|---|---|---|---|---|
| 3.1 | [email protected] | Primary | 9.8 | CRITICAL | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H |
| 3.1 | [email protected] | Secondary | 10 | CRITICAL | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H |
| 3.1 | CNA | DECLARED | 10 | CRITICAL | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H |
CVSS v3.1 Breakdown
Attack Vector
NetworkAttack Complexity
LowPrivileges Required
NoneUser Interaction
NoneScope
UnchangedConfidentiality
HighIntegrity
HighAvailability
HighCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
NVD Known Affected Configurations (CPE 2.3)
Vendor Declared Affected Products
References
| Reference | Source | Link | Tags |
|---|---|---|---|
| github.com/ggerganov/llama.cpp/security/advisories/GHSA-wcr5-566p-9cwj | [email protected] | github.com | Exploit, Vendor Advisory |
| github.com/ggerganov/llama.cpp/commit/b72942fac998672a79a1ae3c03b340f7e6... | [email protected] | github.com | Patch |
| CVE Program record | CVE.ORG | www.cve.org | canonical |
| NVD vulnerability detail | NVD | nvd.nist.gov | canonical, analysis |
No vendor comments have been submitted for this CVE.
There are currently no legacy QID mappings associated with this CVE.