# CVE-2024-58399: llama.cpp before b2731 Out-of-Bounds Read via GGUF Tensor Offsets

Status: published. Published: 2026-10-27. Updated: 2026-11-02.

llama.cpp before b2731 contains an out-of-bounds read vulnerability in llama_model_loader that allows attackers to read memory outside the mapped model file via crafted GGUF tensor offsets. Attackers can supply a crafted or truncated GGUF model file with arbitrary 64-bit tensor offsets to crash the process or load adjacent process memory as model weights.

## Remediation

- fix: The reporting source identifies this reference as a patch. Check the advisory for affected versions and supported release branches. (source: CNA: VulnCheck) — https://github.com/ggml-org/llama.cpp/pull/6885
- fix: The reporting source identifies this reference as a patch. Check the advisory for affected versions and supported release branches. (source: CNA: VulnCheck) — https://github.com/ggml-org/llama.cpp/commit/0ead1f1072fdc70720f92e008a294dc74a826b1d

## Affected products and versions

- ggml-org / llama.cpp (ggml-org/llama.cpp): ≥ b1046; < b2731 (affected, custom). Source: CNA: VulnCheck

## Severity and prioritization

- CVSS 4.0: 6.9 (medium); CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:P/VC:L/VI:N/VA:H/SC:N/SI:N/SA:N; source: CNA: VulnCheck

- CVSS 3.1: 6.1 (medium); CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:L/I:N/A:H; source: CNA: VulnCheck

- CISA KEV: No listing in collected sources

- EPSS: 0.12% as of 2026-11-02; percentile 1.82%

- SSVC: exploitation none; automatable no; technical impact partial; source ADP: CISA-ADP

- Weaknesses: CWE-125

## Exploit evidence

No exploit evidence in collected sources. This is not proof of no exploitation.

## References

- https://github.com/ggml-org/llama.cpp/issues/6774 (CNA: VulnCheck; issue-tracking)

- https://github.com/ggml-org/llama.cpp/pull/6885 (CNA: VulnCheck; patch, issue-tracking)

- https://github.com/ggml-org/llama.cpp/commit/0ead1f1072fdc70720f92e008a294dc74a826b1d (CNA: VulnCheck; patch)

- https://github.com/ggml-org/llama.cpp/blob/b2730/llama.cpp#L3002-L3004 (CNA: VulnCheck; technical-description)

- https://github.com/ggml-org/llama.cpp/releases/tag/b2731 (CNA: VulnCheck; release-notes)

- https://www.vulncheck.com/advisories/llama-cpp-before-b2731-out-of-bounds-read-via-gguf-tensor-offsets (CNA: VulnCheck; third-party-advisory)

## Provenance

- CNA: VulnCheck: https://www.cve.org/CVERecord?id=CVE-2024-58399; retrieved 2026-11-02; source updated 2026-11-02

- FIRST EPSS: https://api.first.org/data/v1/epss?cve=CVE-2024-58399; retrieved 2026-11-02; source updated Not reported

Revision: 460dfc55f9053ce9a4d8f7866a190b534aed6aa005df794a5eda9649a699a373

Canonical: https://y2.dev/cve/CVE-2024-58399

## Agent and API access

Public CVE pages, Markdown, and JSON are free to read without an account or API key.

- Public catalog: https://y2.dev/cve/index.json. Follow nextCursor with the same search, filters, sort, and limit (1–100). A null cursor marks the end.

- WebMCP: search_cve_disclosures, get_cve_disclosure, get_cve_page_markdown, get_y2_cve_access. Available in compatible browsers.

- Cyber API: https://api.y2.dev/api/v2/cyber/cves and https://api.y2.dev/api/v2/cyber/cves/{cveId}.

- Y2 Pro or Elite: create a workspace API key with the intel:cyber scope and send Authorization: Bearer <Y2_API_KEY>. Setup: https://y2.dev/docs/api/create-key.

- x402: Pay per request without an account or API key. Omit Authorization, read the HTTP 402 PAYMENT-REQUIRED challenge, validate its current requirements, and retry with PAYMENT-SIGNATURE through an authorized payment client. These browser tools never make payments. Guide: https://y2.dev/docs/api/x402.

- OpenAPI: https://y2.dev/api/openapi.yaml. Agent access metadata: https://y2.dev/cve/agent.json.

Collected public records only. Check source status for coverage and freshness.