CVE-2025-71439 — llama.cpp before b5649 Heap Out-of-Bounds Read via llama_vocab::impl::print_info
llama.cpp before b5649 contains a heap out-of-bounds read vulnerability in llama_vocab::impl::print_info() that allows attackers to crash model loading via oversized special token IDs. Attackers can supply a crafted GGUF model with a short tokenizer.ggml.tokens array, causing llama-cli or llama-server to read past id_to_token and crash.
Who exploits it and how urgent it is
A 0–100 score combining confirmed exploitation, ransomware and APT use, public exploits, EPSS and severity.
How the score was calculated
- Technical severity (medium)+3
The score orders the patch queue; it does not replace your asset context (internet exposure, criticality, compensating controls).
Triage
Is it exploited, how likely is exploitation, what does it touch, and how severe do the sources call it.
Remediation
Fixes and mitigations documented by the sources — linked to the original advisory.
No fix documented by the sources we poll. That does not mean none exists: check the vendor advisory.
First 24 hours
Ordered from the record’s own fields — exposure first, because you cannot patch what you have not found. A rule-generated starting point.
- Identify exposed assets running the affected vendor/product/version combinations (Ggml-org Llama.cpp).
- No fix documented in the sources: reduce exposure and monitor the vendor advisory.
- Exploitation requires user interaction: tighten email/web filtering and warn affected users.
- Search available logs for exploit probes matching the vulnerability class (memory corruption), errors and authentication anomalies.
Affected scope
Vendor, product and versions as the sources word them.
Attack characteristics
The CVSS vector, decoded. It describes the attack, not your exposure to it.
Every base score collected
Sources score independently and may disagree; each row says who scored it and under which version.
| Score | Version | Severity | Expl. | Impact | Scored by |
|---|---|---|---|---|---|
| 6.8 | CVSS 4.0 | Medium | — | — | disclosure@vulncheck.com via NIST National Vulnerability Database |
| 6.8 | CVSS 4.0 | Medium | — | — | VulnCheck via CVE Program (cve.org) e CISA ADP |
| 5.5 | CVSS 3.1 | Medium | 1.8 | 3.6 | disclosure@vulncheck.com via NIST National Vulnerability Database |
| 5.5 | CVSS 3.1 | Medium | — | — | VulnCheck via CVE Program (cve.org) e CISA ADP |
CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:H (score shown at the top: disclosure@vulncheck.com) Weakness MITRE
Weakness class according to MITRE’s CWE catalog.
Detection
Read off the CVSS vector and the weakness class. Starting points, not tested rules.
- Local/physical vector: focus on endpoint telemetry (EDR) from affected hosts.
- Correlate service crashes/restarts with inbound traffic; repeated crashes may indicate attempts.
Timeline
What happened to this CVE, newest first.
- 2026
- Source status changed · Received → Awaiting Analysis
- Affected products added · ggml-org/llama.cpp
- Record published
- CVSS changed · 5.5
- Source status changed · → Received
- Record created in this database
- CVE published
Source activity
Repeated readings are counted rather than listed.
- 1× References added · Oct 26, 2026 – Oct 26, 2026
- 1× Official description updated · Oct 26, 2026 – Oct 26, 2026
References
6 on the record
- github.com/ggml-org/llama.cpp/commit/c33fe8b8c4427202706b1434e9fc8ab5752c9cac
- github.com/ggml-org/llama.cpp/pull/14145
- github.com/ggml-org/llama.cpp/blob/b5648/src/llama-vocab.cpp
- github.com/ggml-org/llama.cpp/security/advisories/GHSA-g4cc-763q-h9h6
- github.com/ggml-org/llama.cpp/releases/tag/b5649
- www.vulncheck.com/advisories/llama-cpp-before-b5649-heap-out-of-bounds-read-via-llama-v
Elsewhere on this site
Related CVEs (same products)
- Medium CVE-2026-116840 llama.cpp b5854 before b11275 Integer Overflow in gguf_init_from_reader 17h
- High CVE-2026-116816 llama.cpp b5899 before b10261 Heap Out-of-Bounds Write via plamo2 Tokenizer 17h
- Medium CVE-2026-116829 llama.cpp b10398 before b11301 Integer Overflow in gguf_init_from_reader 17h
- High CVE-2024-58400 llama.cpp before b3701 Out-of-Bounds Read in llama_decode via Token IDs 17h
- Medium CVE-2024-58399 llama.cpp before b2731 Out-of-Bounds Read via GGUF Tensor Offsets 17h
- Medium CVE-2026-116467 ggml-org llama.cpp Mirostat Sampler llama-sampler.cpp assertion 23h
Not in any source we poll
Listed rather than left blank: an empty field and an unmeasured one look identical on screen, and only one is a reason to look elsewhere.
- No FIRST EPSS score.
- No fixed version, patch or mitigation documented.
- No CISA SSVC assessment.
- No confirmed IOCs, IP addresses, domains, file hashes, or malware artifacts supplied.
- No organization-specific asset inventory, compensating-control status, or patch deployment evidence supplied.
- No exploit packet captures, log samples, or incident case IDs supplied.
Answered from this record
Text assembled only from the fields above — no additional claims.
What should defenders know first?
CVE-2025-71439 is "llama.cpp before b5649 Heap Out-of-Bounds Read via llama_vocab::impl::print_info", rated Medium. It affects Llama.cpp (Ggml-org); versions are in the scope table. It is not in CISA KEV, which does not rule out exploitation. CVSS 5.5 describes technical severity. First verify whether exposed or business-critical assets run the affected versions, apply vendor fixes or mitigations, and preserve logs for review.
Comments
Moderated technical discussion. Read the community guidelines.
No comments yet.
Sign in or create an account to comment and suggest corrections.