CVE-2024-42479: llama.cpp allows write-what-where in rpc_server::set_tensor
Vulnerability summary
CVE-2024-42479 is a critical (CVSS 10.0) Write-what-where Condition vulnerability in ggerganov llama.cpp. EPSS estimates a 2.61% chance of exploitation in the next 30 days, higher than 85.7% of scored vulnerabilities. 1 public exploit is recorded.
Public exploit (GitHub, Date unknown)
Source freshness unavailable
How is this decided?Timeline
- 12-08-2024PublishedVulnerability first disclosed.
- 13-08-2024Last modifiedVulnerability information updated.
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.
CVSS metrics
2 scores · 2 sources · 1 version- NVDNIST9.8CriticalCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:HDiffers
EPSS trend
Probability
2.61%
Chance of exploitation in the next 30 days
Percentile
86%
Versus all other CVEs
30-day change
No change 0.00 pp
From 2.61% on 21-10-2026
Known exploited
Compare KEV catalogsNot in the CISA KEV catalog.
Not in the ENISA CNW catalog.
Not in the CIRCL catalog.
Public exploits
1 foundLlama.Cpp
Maturity: poc
Weaknesses
CWE · root causeAffected systems
Known conditions: network-reachable, no authentication, no user interaction (CVSS vector). Other conditions: not stated in public data.
Ggerganov1 product
- llama.cpp< b3561
Ggml1 product
- llama.cpp< b3561
2 vendors · 2 products
References
2 links- github.com/ggerganov/llama.cpp/security/advisories/GHSA-wcr5-566p-9cwjX Refsource CONFIRMExploitVendor Advisory