CVE-2025-71439llama.cpp before b5649 Heap Out-of-Bounds Read via llama_vocab::impl::print_info
- 6.8MediumCVSS base score
- 0.12%Exploitation in 30 daysEPSS · top 98% of all CVEs
- NoKnown exploitednot in CISA's KEV catalog
- YesPublic exploitsa reference or SSVC says so
Description
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.
Public exploit
An exploit or proof of concept is public: anyone can try it against an unpatched system. A reference of the record is tagged as an exploit. CISA's SSVC rates its exploitation: a proof of concept is public.
Show the exploits1
References tagged exploit1 reference
- GitHub Security Advisory (GHSA-g4cc-763q-h9h6) (opens in a new tab)vendor-advisoryexploit
Timeline
ID reserved
By VulnCheck
Published
- 9 days later
· 9 days later
Record updated
Changes after publication (a new score, a public exploit, EPSS crossing 1, 10 or 50 %, leaving KEV) are kept since November 2026; earlier ones are not known.
Scores
| Scored by | CVSS | Score | Vector |
|---|---|---|---|
| VulnCheckCNA (assigner) | 4.0 | Medium6.8 | CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:P/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N |
| VulnCheckCNA (assigner) | 3.1 | Medium5.5 | CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:H |
| NVDNVD · Awaiting Analysis | 4.0 | Medium6.8 | CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:P/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X |
- EPSS (exploitation in 30 days)
- 0.12% · top 98% of all CVEs (17 Nov 2026)
- CISA SSVC
- Exploitation: poc · Automatable: no · Technical impact: partial
The list uses the assigner's score when there is one, then CISA's, then NVD's: Medium 6.8.
Affected products
References
References6
- GitHub Security Advisory (GHSA-g4cc-763q-h9h6) (opens in a new tab)vendor-advisoryexploit
- https://github.com/ggml-org/llama.cpp/pull/14145 (opens in a new tab)patchissue-tracking
- https://github.com/ggml-org/llama.cpp/commit/c33fe8b8c4427202706b1434e9fc8ab5752c9cac (opens in a new tab)patch
- https://github.com/ggml-org/llama.cpp/blob/b5648/src/llama-vocab.cpp#L2771 (opens in a new tab)technical-description
- llama.cpp b5649 Release Notes (opens in a new tab)release-notes
- VulnCheck Advisory: llama.cpp before b5649 Heap Out-of-Bounds Read via llama_vocab::impl::print_info (opens in a new tab)third-party-advisory
Sources
The same CVE in the primary databases and aggregators, to check against.
- CVE.org record (opens in a new tab)
- CVE List JSON (GitHub) (opens in a new tab)
- NVD (opens in a new tab)
- FIRST EPSS (opens in a new tab)
- EUVD EUVD-2025-211201 (opens in a new tab)
- OSV.dev (opens in a new tab)
- GitHub Advisories (opens in a new tab)
- CIRCL Vulnerability-Lookup (opens in a new tab)
Badge for a README or a ticket
[](https://cveledger.app/cve/CVE-2025-71439)Record last updated .