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
Affects llama.cppSource GCVE Database
Not known to be exploited · CVSS 8.8 High.
Data as of 28 Oct 2026, 22:28 UTC
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
Affected software
| Product | Affected | Fixed in |
|---|---|---|
Ubuntu 26.10llama.cpppkg:deb/ubuntu/llama.cpp?arch=source&distro=stonkingOther threats | Affected
| Fixed in– |
Ubuntu 26.04 LTSllama.cpppkg:deb/ubuntu/llama.cpp?arch=source&distro=resoluteOther threats | Affected
| Fixed in– |
Check your own hosts for these packages with threat-finder (opens in a new tab), our free open-source scanner.
Description
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.
References
- ubuntu.com/security/CVE-2024-58400 (opens in a new tab)
- cve.org/CVERecord?id=CVE-2024-58400 (opens in a new tab)
- github.com/cveproject/cvelistv5/tree/main/cves/2024/58xxx/cve-2024-58400.json (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/commit/eae597182cb61bbde0b26e7cec5999d28b9327fe (opens in a new tab)
- github.com/ggml-org/llama.cpp/commit/faf69d4237c9ae4d7f572b4674d1002463e8acd3 (opens in a new tab)
- github.com/ggml-org/llama.cpp/pull/9359 (opens in a new tab)
- github.com/ggml-org/llama.cpp/releases/tag/b3701 (opens in a new tab)
- nvd.nist.gov/vuln/detail/cve-2024-58400 (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)