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.
CVE-2024-58400
HIGHPre-NVD 8.28.2Trending — 5 sources updated this week
EchelonGraph scoreHIGH confidence
“—” beside the score: it is equal to the CVSS score beside it.
Score 8.2 from GitHub Security Advisory (severity: HIGH) published 2026-10-27. A secondary CVSS source baseline 8.2; sources differ by 0.0.
Triggered by: GitHub Security Advisory CVSS
Sources: GitHub Security Advisory, a secondary CVSS source
Also known asEUVD-2024-55827 (ENISA EUVD) · GHSA-7wfj-q343-9m2r (GitHub Security Advisories)Source: ENISA EUVD
8.2EG
EchelonGraph verdictPlan a fixRemediate within your standard update timelines at low or medium mission impact and sooner than that at high (the SSVC decision on this page).
- High severity, but no confirmed exploitation yet
CISA-KEV: Not listedEPSS PROB: 0.4%CVSS: 8.2Exploit: None knownExposed services: Not assessed
A fix is available — apply it.
- CVSS v3
- 8.2
- EG Score
- 8.2HIGHhigh confidence
- EG Risk
- 52EG Risk 52/100
EG Risk is EchelonGraph's 0–100 priority score. It fuses impact severity (EG Severity, the CVSS base score, never the KEV-floored or EPSS-lifted EG Score) with real-world exploitation and automatability, under weights EchelonGraph set by hand, so you can rank equal-severity CVEs and fix the most dangerous first. Higher = act sooner.
How it’s computed (value × EchelonGraph’s weight)Severity82% × 45%Impact severity (EG Severity): CVSS 8.2 of 10. Never the KEV-floored or EPSS-lifted EG Score.Exploitation0% × 40%No KEV listing, EG-KEV tier or EPSS when EchelonGraph scored this CVE.Automatability100% × 15%CISA's SSVC Automatable value: yes (Vulnrichment).SSVC (CISA's decision table, applied by EchelonGraph): Track at low or medium mission impact; Attend at high (mission-essential systems).Exploitation none (CISA Vulnrichment) · Automatable yes (CISA Vulnrichment) · Technical impact partial (CISA Vulnrichment). All three are CISA's SSVC values (Vulnrichment). EchelonGraph applied CISA's decision table to them; CISA publishes SSVC inputs and the table, not a decision for each CVE.Action: A fix is available. Apply it within your standard update timelines at low or medium mission impact and sooner than that at high. - EPSS PROB
- 0.4%
- EPSS %ILE
- 36th
- KEV
- Not listed
What the EG score is made of (scorer v4.0: the three questions the 0–10 score mixes, published apart · methodology)
The EG score (8.2): severity, escalated by confirmed exploitation. This CVE's 8.2 is its impact severity (EG Severity), not escalated.
- EG Severity
- 8.2 HIGHCVSS-B, impact only: no KEV listing, EPSS or EG-KEV tier raises it.GitHub Security Advisory CVSS
- EG Likelihood
- 0.4% within 30 daysSource: FIRST EPSS. FIRST's exploitation probability, not an EchelonGraph model.
- Confirmed exploitation
- None on record (CISA KEV, EG-KEV Tier 1)Reported apart from the likelihood: an observed fact, not a probability.
- EG Priority
- SSVC Track at medium mission impactTrack at low or medium mission impact; Attend at high (mission-essential systems).CISA BOD 26-04: 14 days if the affected system is publicly exposed; 60 days if it is not.Each input and its source: the SSVC and BOD 26-04 blocks below.
SSVC (CISA's decision table, applied by EchelonGraph)Track at low or medium mission impact; Attend at high (mission-essential systems).
A fix is available. Apply it within your standard update timelines at low or medium mission impact and sooner than that at high.
Exploitation none (CISA Vulnrichment) · Automatable yes (CISA Vulnrichment) · Technical impact partial (CISA Vulnrichment). All three are CISA's SSVC values (Vulnrichment). EchelonGraph applied CISA's decision table to them; CISA publishes SSVC inputs and the table, not a decision for each CVE. Mission impact is CISA's Mission & Well-being decision point, and only you can judge it. CISA's table makes it high when Mission Prevalence is Essential — the vulnerable component "directly provides capabilities that constitute at least one MEF for at least one entity" (MEF: mission essential function) — or when Public Well-Being Impact is Irreversible: "multiple fatalities are likely", the cyber-physical system "is likely lost or destroyed", "extreme or serious externalities" are imposed on other parties, or social systems such as elections or the financial grid "are destabilized and potentially collapse". CISA's decision table
BOD 26-04 (CISA's remediation timeline, Table 1)14 days if the affected system is publicly exposed; 60 days if it is not.
In CISA KEV no (CISA's KEV catalog) · Automatable yes (CISA Vulnrichment) · Technical impact partial (CISA Vulnrichment). Whether your system is publicly exposed is yours to answer. BOD 26-04 binds US Federal Civilian Executive Branch agencies; for anyone else it is CISA's published timeline, a reference rather than an obligation. The directive · how EchelonGraph applies it
Published
October 27, 2026
Last Modified
October 27, 2026
Advisory Details (6)
Auto-updated Oct 27, 2026Patch available. Sources: github_commit, github_pr, github_release.
Web page
llama.cpp before b3701 Out-of-Bounds Read in llama_decode via Token IDs | Advisories | VulnCheck
https://www.vulncheck.com/advisories/llama-cpp-before-b3701-out-of-bounds-read-in-llama-decode-via-token-idsGitHub release Patch Available
b3701
Patch available: ggml-org/llama.cpp b3701
https://github.com/ggml-org/llama.cpp/releases/tag/b3701GitHub pull request
llama : sanitize tokens in the upper bound
Fix merged in ggml-org/llama.cpp PR #9359 on 2024-09-08 — awaiting tagged release
https://github.com/ggml-org/llama.cpp/pull/9359GitHub commit
commit faf69d4237c9 (ggml-org/llama.cpp)
Fix landed in ggml-org/llama.cpp commit faf69d4237c9 — awaiting tagged release
https://github.com/ggml-org/llama.cpp/commit/faf69d4237c9ae4d7f572b4674d1002463e8acd3GitHub commit
commit eae597182cb6 (ggml-org/llama.cpp)
Fix landed in ggml-org/llama.cpp commit eae597182cb6 — awaiting tagged release
https://github.com/ggml-org/llama.cpp/commit/eae597182cb61bbde0b26e7cec5999d28b9327feWeb page
llama.cpp/examples/server/server.cpp at b3681 · ggml-org/llama.cpp · GitHub
https://github.com/ggml-org/llama.cpp/blob/b3681/examples/server/server.cpp#L789Vendor Advisories for CVE-2024-58400(1)
These vendors published their own advisory mentioning this CVE — often with vendor-specific remediation steps + affected product lists not in NVD.
Weakness Classification(1)
MITRE Common Weakness Enumeration — the root-cause categories this CVE belongs to.
Data Freshness Timeline
(refreshed 9× in last 7d / 9× in last 30d)
Each row is a time one of our pipelines fetched, updated or re-scored this CVE. For example, "NVD update" means NVD published or revised its analysis for this CVE; "MITRE cvelistV5" means we ingested or refreshed it from the CNA feed. An arrow marks a change the record states ("CVSS v3 → 9.1"); EPSS and GHSA rows show the values recorded at that time, not what changed (EPSS values are rounded; hover one for the exact figures). Most recent first.
- 2026-10-27 16:30 UTCEPSS rescoreEPSS 0.4% · 36th percentile
- 2026-10-27 16:08 UTCEG score recompute
- 2026-10-27 16:08 UTCGHSA enrichmentGHSA-7wfj-q343-9m2r · GitHub severity HIGH · GitHub CVSS 8.2
- 2026-10-27 14:20 UTCEG score recompute
- 2026-10-27 14:20 UTCGHSA enrichmentGHSA-7wfj-q343-9m2r · GitHub severity HIGH · GitHub CVSS 8.2
- 2026-10-27 02:01 UTCENISA EUVD ID recordedEUVD-2024-55827 · Source: ENISA EUVD
- 2026-10-27 01:29 UTCEG score recompute
- 2026-10-27 01:11 UTCEG score recomputeFirst assessed: 8.2 HIGH
- 2026-10-27 01:10 UTCMITRE cvelistV5first tracked
Related CVEs(same CWE)
Frequently asked(5)
What is CVE-2024-58400?
CVE-2024-58400 is a high-severity vulnerability; its CVE record was published on October 27, 2026. llama.cpp before b3701 contains an out-of-bounds read vulnerability in llamadecodeinternal and llamaencodeinternal 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…
When was CVE-2024-58400 made public?
CVE-2024-58400 was made public on September 8, 2024: that is the date its CVE record's CNA, VulnCheck, gives for when the vulnerability was made public. The CVE record itself was published on October 27, 2026. EchelonGraph's copy of the record carries a last-modified date of October 27, 2026; the record at its source may have been updated since.
Is CVE-2024-58400 actively exploited?
CVE-2024-58400 is not currently on CISA's Known Exploited Vulnerabilities catalog. FIRST EPSS estimates a 0.4% probability of exploitation in the next 30 days (36th percentile of EPSS-scored CVEs).
What is the CVSS score of CVE-2024-58400?
CVE-2024-58400 has a CVSS base score of 8.2 (a secondary CVSS source that NVD displays; NVD's own analysis pending).
How do I remediate CVE-2024-58400?
A fix for CVE-2024-58400 is available: update to the fixed version the vendor names in its advisory. The vendor advisories EchelonGraph has for CVE-2024-58400 are linked in the Vendor Advisories panel on this page.
Dependency Blast Radius
Explore the affected products and dependency analysis for CVE-2024-58400
Is Your Infrastructure Affected by CVE-2024-58400?
EchelonGraph automatically scans your cloud infrastructure and maps CVE exposure using blast radius analysis.