CVE-2024-58400

llama.cpp before b3701 Out-of-Bounds Read in llama_decode via Token IDs

Published Oct 27, 2026 CVSS 4.0 · 8.8 High EPSS < 1% KEV · Not listed

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.

Affected Products

Default status is the baseline for the product, each version can override it (e.g. patched versions marked unaffected).

Vendor Product Default status Versions

ggml-org

llama.cpp

unaffected

Version	Status	Constraints
`0`	affected	< b3701

No data.

Vendor Product Versions

Ggml

Llama.cpp

Version	Status	Scheme	Platform
`[0,b3701)`	affected	generic	—

Ggml-org

Llama.cpp

Version	Status	Scheme	Platform
`[0,b3701)`	affected	generic	—

Remediation

No solution or workaround provided in the CVE record

Tracking

Advisories

No advisories available

Metrics

Attack Vector Network

Attack Complexity Low

Privileges Required None

Attack Requirements None

User Interaction None

Vulnerable System Confidentiality Impact Low

Vulnerable System Integrity Impact None

Vulnerable System Availability Impact High

Subsequent System Confidentiality Impact None

Subsequent System Integrity Impact None

Subsequent System Availability Impact None

Attack Vector Network

Attack Complexity Low

Privileges Required None

Scope Unchanged

Confidentiality Impact Low

Integrity Impact None

Availability Impact High

User Interaction None

No CVSS v3.0

No CVSS v2

This CVE is not in the KEV list.

Exploit prediction score: < 1% (0.422% probability within 30 days)

Exploitation none

Automatable yes

Technical Impact partial

References

Link	Providers
https://github.com/ggml-org/llama.cpp/blob/b3681/examples/server/server.cpp#L789
https://github.com/ggml-org/llama.cpp/commit/eae597182cb61bbde0b26e7cec5999d28b9327fe
https://github.com/ggml-org/llama.cpp/commit/faf69d4237c9ae4d7f572b4674d1002463e8acd3
https://github.com/ggml-org/llama.cpp/pull/9359
https://github.com/ggml-org/llama.cpp/releases/tag/b3701
https://www.vulncheck.com/advisories/llama-cpp-before-b3701-out-of-bounds-read-in-llama-decode-via-token-ids

History

Oct 27, 2026 3:30 PM Scoring metrics updated View changes

Type	Values Removed	Values Added
Metrics		ssvc `{'options': {'Automatable': 'yes', 'Exploitation': 'none', 'Technical Impact': 'partial'}, 'version': '2.0.3'}`

Oct 27, 2026 7:00 AM First appearance in the feed. Affected vendors updated View changes

Type	Values Removed	Values Added
First Time appeared		Ggml-org Ggml-org llama.cpp
Vendors & Products		Ggml-org Ggml-org llama.cpp

Oct 27, 2026 4:30 AM Description updated. Title updated. First appearance in the feed. Weaknesses updated. Affected versions updated. Affected vendors updated. Added references. Scoring metrics updated View changes

Type	Values Removed	Values Added
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.
Title		llama.cpp before b3701 Out-of-Bounds Read in llama_decode via Token IDs
First Time appeared		Ggml Ggml llama.cpp
Weaknesses		CWE-129
CPEs		cpe:2.3:a:ggml:llama.cpp::::::::
Vendors & Products		Ggml Ggml llama.cpp
References		https://github.com/ggml-org/llama.cpp/blob/b3681/examples/server/server.cpp#L789 https://github.com/ggml-org/llama.cpp/commit/eae597182cb61bbde0b26e7cec5999d28b9327fe https://github.com/ggml-org/llama.cpp/commit/faf69d4237c9ae4d7f572b4674d1002463e8acd3 https://github.com/ggml-org/llama.cpp/pull/9359 https://github.com/ggml-org/llama.cpp/releases/tag/b3701 https://www.vulncheck.com/advisories/llama-cpp-before-b3701-out-of-bounds-read-in-llama-decode-via-token-ids
Metrics		cvssV3_1 `{'score': 8.2, 'vector': 'CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:H'}` cvssV4_0 `{'score': 8.8, 'vector': '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'}`