CVE-2024-58400: ggml-org llama.cpp · Improper Validation of Array Index
Affects ggml-org llama.cppSource CVE Database V5
Not known to be exploited · CVSS 8.8 High : upgrade to b3701 soon.
Data as of 27 Oct 2026, 01:27 UTC
- Patch
- Available – fixed in b3701
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:L/VI:N/VA:H/SC:N/SI:N/SA:NExploitation evidence
Disclosed: evidence found.
CVE published 27 Oct 2026
Detectable: no evidence on record.
No public nuclei template indexed
Weaponised: no evidence on record.
No public exploit code indexed in Metasploit or Exploit-DB
Exploited in the wildExploited: no evidence on record.
Not in CISA KEV and no source reports exploitation
Observed by OffSeq MirageSeen by Mirage: no evidence on record.
No attack traffic recorded by OffSeq Mirage sensors
A missing step is not evidence of safety. Sources: cve.org (opens in a new tab), the Metasploit, Exploit-DB and nuclei-templates index as of 26 Oct 2026.
What to do
Upgrade ggml-org llama.cpp to b3701.
Affected software
| Product | Affected | Fixed in |
|---|---|---|
| ggml-orgllama.cpp | Affected
| Fixed in
|
GitHubllama.cpppkg:github/llama.cppOther threats | Affected
| Fixed in
|
Check your own hosts for these packages with threat-finder (opens in a new tab), our free open-source scanner.
AI-suggested
A fix is available in llama.cpp version b3701. Users should upgrade to version b3701 or later to remediate this vulnerability. No additional mitigation steps are indicated.
Description
CVE-2024-58400 is an out-of-bounds read vulnerability in llama.cpp before version b3701. It occurs in the functions llama_decode_internal and llama_encode_internal due to improper validation of array indices. Remote unauthenticated attackers can exploit this by sending integer-array prompts with token IDs outside the valid range to the llama-server /completion endpoint, potentially reading memory beyond the intended embedding array or causing a crash.
References
- github.com/ggml-org/llama.cpp/pull/9359 (opens in a new tab)
- github.com/ggml-org/llama.cpp/commit/faf69d4237c9ae4d7f572b4674d1002463e8acd3 (opens in a new tab)
- github.com/ggml-org/llama.cpp/commit/eae597182cb61bbde0b26e7cec5999d28b9327fe (opens in a new tab)
- github.com/ggml-org/llama.cpp/blob/b3681/examples/server/server.cpp (opens in a new tab)
- github.com/ggml-org/llama.cpp/releases/tag/b3701 (opens in a new tab)
- vulncheck.com/advisories/llama-cpp-before-b3701-out-of-bounds-read-in-llama-decode-via-token-ids (opens in a new tab)