Buffer overflow in Ggerganov Llama.cpp
CVE-2024-42479
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.
EPSS: 0.026 (83.8th percentile) — read the EPSS interpretation.
CVSS v3 metric
CVSS v3 base score 10.0 (Critical). Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H.
Affected products
- Ggerganov Llama.cpp — versions < b3561
- Ggml Llama.cpp
Weakness classification (CWE)
Public proof-of-concept exploits
References
- security-advisories@github.com (x_refsource_CONFIRM, Exploit, Vendor Advisory)
- security-advisories@github.com (Patch, x_refsource_MISC)
Frequently asked questions
- What is CVE-2024-42479?
- CVE-2024-42479 is a critical-severity vulnerability in Ggerganov Llama.cpp, classified under Write-what-where Condition. CVSS score: 10.0/10. Published 2024-08-12.
- How severe is CVE-2024-42479?
- Critical severity. CVSS v3 base score is 10.0 out of 10.
- Is CVE-2024-42479 known to be exploited?
- 3 public proof-of-concept repositories are indexed. Not currently listed in the CISA KEV catalog.