Evidence used
- No CISA KEV confirmation is currently recorded.
- A structured source references public exploit or proof-of-concept material.
- EPSS is 0.52% for the current model date.
BlackTreeCVE IntelligenceFull vulnerability report · 2025
CVE-2025-49847High confidence
llama.cpp Vulnerable to Buffer Overflow via Malicious GGUF Model
ggml-org · llama.cpp
Official source article: GitHub GHSA-8WWF-W4QM-GPQR ↗. Check the applicable product and release in the original source.
8.8HighCVSS 3.1
Within 7 days
Patch availableHigh technical severity with public exploit material referenced by a structured source; prioritise exposed affected systems while verifying vendor guidance.
R
Open reassessment dashboard →Operational reassessment
Published severity in operational context
Published severityHigh→Operational priority:Critical, raised one band.upgradedsince 18 Jun 2025
Compensating controls
- Validate the affected product branch and deploy the verified fixed release.
- Restrict the affected network interface to trusted sources where business-safe.
- Increase monitoring for the attack path and post-exploitation behaviour described in the report.
Verification
- Confirm that the asset runs ggml-org llama.cpp and falls inside the recorded affected range.
- Verify the installed build against the product-specific fixed version after deployment.
- Validate exposure, authentication requirements and compensating controls in the actual environment.
- Reopen this reassessment when CVSS, KEV, EPSS, exploit evidence or remediation changes.
Distribution package intelligence
2 package statesRelease-specific package status
Debian findings are scoped to the named distribution, release and source package. An absent finding does not mean a package is unaffected.
Repository candidate not checked
A published vendor fix does not prove that a matching update is enabled and installable on a particular asset. Confirm the local package candidate before scheduling remediation.
| Distribution release | Source package | Vendor state | Fixed version | Evidence |
|---|---|---|---|---|
| Debian forkyforky · source | llama.cpp | Vendor fix publishedDebian records a fixed source-package version for this release. | 5713+dfsg-1 | Debian Security Tracker ↗Source updated 5 Oct 2026 |
| Debian sidsid · source | llama.cpp | Vendor fix publishedDebian records a fixed source-package version for this release. | 5713+dfsg-1 | Debian Security Tracker ↗Source updated 5 Oct 2026 |
Direct vendor intelligence
1 currentAuthoritative vendor CSAF and VEX advisories
Structured product status and remediation from the issuing vendor. Product-state explanations are always visible; large lists can be searched or downloaded.
CVE-2025-49847 · CSAF 2.0 · revision 2 · interimSUSE Product Security TeamCVE-2025-49847
The vendor recommends these product versions as the target state.
- ggml-devel-5699-1.1 as component of openSUSE Tumbleweed
- libggml-5699-1.1 as component of openSUSE Tumbleweed
- libggml-base-5699-1.1 as component of openSUSE Tumbleweed
- libggml-cpu-5699-1.1 as component of openSUSE Tumbleweed
- libggml-opencl-5699-1.1 as component of openSUSE Tumbleweed
- libggml-vulkan-5699-1.1 as component of openSUSE Tumbleweed
- libllama-5699-1.1 as component of openSUSE Tumbleweed
- libmtmd-5699-1.1 as component of openSUSE Tumbleweed
- llamacpp-5699-1.1 as component of openSUSE Tumbleweed
- llamacpp-devel-5699-1.1 as component of openSUSE Tumbleweed
- Summary
- 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.
- Remediation
- To install this SUSE Security Update use the SUSE recommended installation methods like YaST online_update or "zypper patch".
High technical severity with public exploit material referenced by a structured source; prioritise exposed affected systems while verifying vendor guidance.
Patch available01
What, why and how
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.
What
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.
Why
The product performs operations on a memory buffer, but it reads from or writes to a memory location outside the buffer's intended boundary. This may result in read or write operations on unexpected memory locations that could be linked to other variables, data structures, or internal program data.
How
An attacker operating through a network path may attempt exploitation without authentication after a user interaction. If successful, the issue may cause the confidentiality, integrity or availability impact described by the vendor.
What
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.
Why
The product performs operations on a memory buffer, but it reads from or writes to a memory location outside the buffer's intended boundary. This may result in read or write operations on unexpected memory locations that could be linked to other variables, data structures, or internal program data.
How
An attacker operating through a network path may attempt exploitation without authentication after a user interaction. If successful, the issue may cause the confidentiality, integrity or availability impact described by the vendor.
02
Exploit reality and attack path
CVSS severity, EPSS forecast probability, public exploit material and CISA-confirmed exploitation are separate signals.
Observed exploitation No confirmed evidence
?
Confirmed exploitation and public exploit material are separate signals. Attacks can occur without public proof-of-concept or exploit code.No CISA KEV match was present at the last successful refresh. This means no confirmation from that source, not proof of no exploitation.
Public PoC / exploit material Reference recorded
?
Confirmed exploitation and public exploit material are separate signals. Attacks can occur without public proof-of-concept or exploit code.CISA Vulnrichment records proof-of-concept exploitation in its SSVC data. BlackTree has not independently executed or validated exploit material.
- Likely attack path
- a network path → Improper Restriction of Operations within the Bounds of a Memory Buffer → cause the confidentiality, integrity or availability impact described by the vendor
- Attack surface
- Network
- Privileges required
- None: unauthenticated exploitation is possible
- User interaction
- Required interaction required
- Attack complexity
- Low: no specialised conditions are recorded
- Security boundary
- Unchanged: impact remains within the vulnerable component's security authority
- Weakness
?
CWE means Common Weakness Enumeration: a standard category for the underlying weakness. - CWE-119 ↗
CWE-119: Improper Restriction of Operations within the Bounds of a Memory Buffer. The product performs operations on a memory buffer, but it reads from or writes to a memory location outside the buffer's intended boundary. This may result in read or write operations on unexpected memory locations that could be linked to other variables, data structures, or internal program data.
- CVSS vector
?
CVSS means Common Vulnerability Scoring System. The vector records the metric values used to calculate technical severity. CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:HCommon Vulnerability Scoring System 3.1: the compact vector below is decoded into plain language.
AVNetworkAttack vector: The vulnerable component can be reached over a network.ACLowAttack complexity: No specialised conditions are required beyond attacker-controlled input.PRNonePrivileges required: The attacker does not need an account or existing privileges.UIRequiredUser interaction: Another user must perform an action for exploitation to succeed.SUnchangedScope: The security impact remains within the vulnerable component's authority.CHighConfidentiality impact: A successful attack can cause a major loss.IHighIntegrity impact: A successful attack can cause a major loss.AHighAvailability impact: A successful attack can cause a major loss.- Post-exploitation / living off the land
- Stolen credentials, tokens and legitimate administration functions may provide continued access without deploying a large custom toolset.
03
Patch and workaround
Operational remediation based on structured source evidence.
- Status
?
Patch availability is based on structured fixed-version fields and authoritative update references. If no fix is verified, check the vendor advisory before making a change. - Patch available
- Affected
- llama.cpp: < b5662
- Action
- To install this SUSE Security Update use the SUSE recommended installation methods like YaST online_update or "zypper patch".
- Workaround
- A mitigation or workaround reference is available from the source linked below; validate it against the affected product and version.
04
Evidence and provenance
Published 17 Jun 2025 · Last source change 18 Jun 2025, 13:41 UTC · CWE-119 · Improper Restriction of Operations within the Bounds of a Memory Buffer
CVE recordCVE.org · 5.1
CVSS sourceCNA
EPSS source FIRST · tracked since 2026-08-14
?
The date BlackTree first stored a score for this CVE from the daily FIRST EPSS feed.European sourceENISA EUVD · EUVD-2025-18632
Product sourceCNA
Remediation sourceVendor CSAF · SUSE Product Security Team
CWE sourceCNA
NVD statusNVD enriched
Core structured fields are present and their contributing authorities are shown above.
Material change intelligence
View recent updates ↗What changed after publication
No material field changes have been recorded since change tracking began. Routine source refreshes and cosmetic edits are intentionally excluded.
Technical terms and abbreviations used in this report
- CVE
- Common Vulnerabilities and Exposures: the public identifier for one disclosed vulnerability.
- CVSS
- Common Vulnerability Scoring System: a technical severity framework; it is not patching priority by itself.
- EPSS
- Exploit Prediction Scoring System: FIRST's estimate of the probability that exploitation activity will be observed in the next 30 days; it is a forecast, not confirmation.
- CWE
- Common Weakness Enumeration: the standard category describing the underlying software or hardware weakness.
- CNA
- CVE Numbering Authority: an organisation authorised to assign and publish CVE records.
- CISA ADP
- Cybersecurity and Infrastructure Security Agency Authorized Data Publisher: structured enrichment added to a CVE record.
- NVD
- National Vulnerability Database: NIST's enrichment service for CVE records.
- CERT / CSIRT
- A computer security incident response team that publishes warnings or coordinates incident response.
- PoC
- Proof of concept: public material that demonstrates or helps reproduce exploitation.
- CSAF
- Common Security Advisory Framework: a machine-readable format for security advisories.
- LoTL
- Living off the land: abuse of legitimate tools or system functions during an attack.