CVE-2025-49847: llama.cpp Vulnerable to Buffer Overflow via Malicious GGUF Model
Noroxi assessment
Priority: Monitor (action score 35/100)
- The sources we track (CISA KEV, Exploit-DB, Metasploit, Nuclei, GitHub) show no public exploit code or exploitation in the wild.
- Probability of exploitation in the next 30 days: 0.51% (FIRST EPSS).
- Anyone who can reach it over the internet can trigger it. No account or password is required. A user must open a link or visit a page. No special conditions are required; it is repeatable.
- Fixed version: llama.cpp (Debian:14) 5713+dfsg-1; llamacpp (openSUSE:Tumbleweed) 5699-1.1.
Low priority for now. Upgrade to llama.cpp (Debian:14) 5713+dfsg-1; llamacpp (openSUSE:Tumbleweed) 5699-1.1 or later.
Generated automatically from the record's data: CVSS (NVD and CNA), CISA KEV and SSVC, FIRST EPSS, exploit sources, fixed versions. How we calculate it
Primary sources: NVD · CVE.org · FIRST EPSS
llama.cpp is an inference of several LLM models in C/C++. Prior to version b5662, an attacker‐supplied GGUF model vocabulary can trigger a buffer overflow in llama.cpp’s vocabulary‐loading code. Specifically, the helper _try_copy in llama.cpp/src/vocab.cpp: llama_vocab::impl::token_to_piece() casts a very large size_t token length into an int32_t, causing the length check (if (length < (int32_t)size)) to be bypassed. As a result, memcpy is still called with that oversized size, letting a malicious model overwrite memory beyond the intended buffer. This can lead to arbitrary memory corruption and potential code execution. This issue has been patched in version b5662.
- Published
- Jun 17, 2025
- Updated
- Jun 17, 2026
- EPSS
- 0.5% · 44th percentile
- CWE
- CWE-119
Report tools
Action score
35
Monitor
Low priority for now.
- CVSS
- 35 / 40 · 8.8 / 10
- CISA KEV
- 0 / 30 · Not listed
- EPSS
- 0 / 30 · 0.5%
CISA SSVC decision
- Exploitation
- proof of concept
- Automatable
- no
- Technical impact
- total
Vulnrichment: CISA's decision-tree inputs.
CNA vs NVD score
- NVD
- —
- CNA · GitHub_M
- 8.8
- NVD has not scored this yet; the score shown is the CNA’s.
The score given by the assigning authority versus NVD’s independent score. A gap means the severity is contested.
Get told when this record changes
- Not in KEV: no record of exploitation in the wild
- No public exploit code on record
- A fix has been released
If any of these changes, we'll tell you in the daily email digest.
Running WordPress? Scan your site free with WP Lens
Noroxi analysis
What does it mean in your environment?
The assessment above is generated automatically from the record's data; it doesn't know your environment. Our team verifies on your systems whether this vulnerability is actually exploitable and which mitigation is enough.
We use this product, ask for helpAffected systems
Is your version affected?
Pick the product and type the version you run. It's compared with this record's version ranges in your browser; the version isn't sent anywhere.
| Vendor | Product | CPE |
|---|---|---|
| ggml | llama.cpp | cpe:2.3:a:ggml:llama.cpp |
Affected versions
NVD version ranges (for catalog products). Add the product to your stack with a version and matching uses these.
- ggml llama.cppbefore b5662
Versions reported by the vendor
Affected version ranges reported by the assigning authority (GitHub_M). Independent of NVD's CPE analysis and usually ahead of it.
ggml-org llama.cpp
- < b5662affected
Package-level exposure
OSV and GitHub Advisory data: ecosystem, package and range. SBOM matching uses this table.
| Ecosystem | Package | Affected range | Fix |
|---|---|---|---|
| Debian:14 | llama.cpp | before 5713+dfsg-1 | 5713+dfsg-1 |
| openSUSE:Tumbleweed | llamacpp | before 5699-1.1 | 5699-1.1 |
Same product
ggml: all recordsOther highest-scoring records for the same primary product.
- CVE-2024-42479llama.cpp allows write-what-where in rpc_server::set_tensor40Plan
- CVE-2026-34159llama.cpp: Unauthenticated RCE via GRAPH_COMPUTE buffer=0 bypass in llama.cpp RPC backend39Monitor
- CVE-2026-21869llama.cpp has Out-of-bounds Write in llama-server39Monitor
Published before and after this one in the same product
- ← EarlierCVE-2024-42477Aug 12, 2024 · llama.cpp global-buffer-overflow in ggml_type_size30Monitor
- ← EarlierCVE-2024-42478Aug 12, 2024 · llama.cpp allows Arbitrary Address Read in rpc_server::get_tensor39Monitor
- Later →CVE-2025-52566Jun 24, 2025 · llama.cpp tokenizer signed vs. unsigned heap overflow35Monitor
Remediation
Which version to upgrade to
Fix versions compiled from the vendor, package registries and Microsoft. Verify the vendor's note before upgrading.
| Product / package | Fixed version | Source |
|---|---|---|
| debian:llama.cpp | 5713+dfsg-1 · Debian:14 | Package registry (OSV) |
| opensuse:llamacpp | 5699-1.1 · openSUSE:Tumbleweed | Package registry (OSV) |
Exploit status
No known public exploit
No public exploit has been observed yet. That doesn't mean you're safe, only that the bar is a little higher.
Research context
For pentesters and researchers: attack profile, score disagreement, timeline, patch commits, credits, variant and chain candidates, bug bounty scope. All derived from existing data; no exploit code.
Timeline
From publication to today: proof of concept, Metasploit module, CISA KEV and fix record. Dates are as reported by the sources.
No dated events beyond publication.
No history yet (it accumulates with the daily EPSS job).
Patch and commit links
Commit, PR and diff links among the references. A starting point for patch-diffing and variant hunting; fixes, not exploits.
Credits
All researchersFinders, reporters and analysts named in the CNA record. Click a name for that researcher’s other records.
No credits in the CNA record.
Variant candidates
Same product, same weakness class, within 18 months. If the patch missed the root cause, the sibling bug is here.
- CVE-2026-34159288 days apartllama.cpp: Unauthenticated RCE via GRAPH_COMPUTE buffer=0 bypass in llama.cpp RPC backend39Monitor
- CVE-2025-525667 days apartllama.cpp tokenizer signed vs. unsigned heap overflow35Monitor
Chain candidates
An authentication bypass and a privilege-requiring bug in the same product, published close together: combined they may become an unauthenticated path.
—
Bug bounty scope
No known public program.
Source: bounty-targets-data (public HackerOne, Bugcrowd, Intigriti, YesWeHack listings).
Technical details
Attack conditions
- Anyone who can reach it over the internet can trigger it.
- No account or password is required.
- A user must open a link or visit a page.
- No special conditions are required; it is repeatable.
If successful
- Confidentiality
- high · data can be read
- Integrity
- high · data or configuration can be modified
- Availability
- high · the service can be disrupted
- Attack vector
- Network
- Attack complexity
- Low
- Privileges required
- None
- User interaction
- Required
- Scope
- Unchanged
- Confidentiality impact
- High
- Integrity impact
- High
- Availability impact
- High
Weakness class (CWE)
CWE-119 · Improper Restriction of Operations within the Bounds of a Memory BufferCVSS vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
nvd-secondary
Attack context
MITRE CAPEC attack patterns and ATT&CK techniques for this weakness class (CWE). A starting point for detection rules and threat hunting.
Attack patterns (CAPEC)
- Buffer Overflow via Environment VariablesCAPEC-10likelihood: High · High
- Overflow BuffersCAPEC-100likelihood: High · Very High
- Buffer ManipulationCAPEC-123likelihood: High · Very High
- Client-side Injection-induced Buffer OverflowCAPEC-14likelihood: Medium · High
- Filter Failure through Buffer OverflowCAPEC-24likelihood: High · High
- MIME ConversionCAPEC-42likelihood: High · High
- Overflow Binary Resource FileCAPEC-44likelihood: High · Very High
- Buffer Overflow via Symbolic LinksCAPEC-45likelihood: High · High
ATT&CK techniques
—
Change log
- Fix✗ → ✓
For records you follow, these changes also arrive as notifications. →
References
Show all references (1 more)Show less
Vendor advisories and official records. Exploit/PoC links are deliberately left out.