CVE-2024-58400 json
llama.cpp before b3701 Out-of-Bounds Read in llama_decode via Token IDs
published 2026-10-27 13 d ago modified 2026-10-27 12 d ago also EUVD-2024-55827
- cvss
- 8.2
- version 3.1, CNA
- cisa kev
- Not listed
- not in CISA's catalog
- epss
- 0.4%
- EPSS 0.4% chance of exploitation in 30 days, percentile 36%
- public exploits
- 0
- none known
Summary
llama.cpp before b3701 contains an out-of-bounds read vulnerability in llama_decode_internal and llama_encode_internal that allows remote unauthenticated attackers to read memory by supplying unvalidated token IDs. Attackers can send integer-array prompts to the llama-server /completion endpoint with IDs outside 0 to n_vocab to read embedding memory out of bounds or crash the process.
Patch / fix
- ggml-org llama.cpp b3701
CISA SSVC
- Exploitation
- none
- Automatable
- yes
- Technical impact
- partial
- Assessed
- 13 d ago
Exploit prediction
0.42% chance of exploitation in the next 30 days, higher than 36% of all scored CVEs (FIRST EPSS, 2026-11-08).
CVSS scores
| assigned by | version | score | vector |
|---|---|---|---|
| CNA | 4.0 | 8.8 | CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:L/VI:N/VA:H/SC:N/SI:N/SA:N |
| CNA | 3.1 | 8.2 | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:H |
| CNA | 4.0 | 8.8 | CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:L/VI:N/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X |
Affected products
- ggml-org llama.cpp
Classification
- Weakness
-
- CWE-129 Improper Validation of Array Index
References
-
github.com
/ggml-org/llama.cpp/pull/9359
patch, issue-tracking
-
github.com
/ggml-org/llama.cpp/commit/faf69d4237c9ae4d7f572b4674d1002463e8acd3
patch
-
github.com
/ggml-org/llama.cpp/commit/eae597182cb61bbde0b26e7cec5999d28b9327fe
patch
-
github.com
/ggml-org/llama.cpp/blob/b3681/examples/server/server.cpp#L789
technical-description
-
github.com
/ggml-org/llama.cpp/releases/tag/b3701
release-notes
-
vulncheck.com
/advisories/llama-cpp-before-b3701-out-of-bounds-read-in-llama-decode-via-token-ids
third-party-advisory
Sources
- CVE List CVE-2024-58400
- NVD CVE-2024-58400
Fencer Vulns keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.
CPEs and fixed versions use Anchore's correction of NVD's data: Added CPE configurations because not yet analyzed by NVD.