Buffer Overflow Vulnerability in Llama.cpp Affects Multiple Large Language Models
CVE-2025-49847

8.8HIGH

Key Information:

Vendor

Ggml-org

Status
Llama.cpp
Vendor
CVE Published:
17 June 2025

What is CVE-2025-49847?

The vulnerability in Llama.cpp stems from inadequate handling of attacker-supplied GGUF model vocabularies, allowing malicious actors to exploit buffer overflow vulnerabilities. In the affected versions, an oversized token length is improperly cast, resulting in bypassing critical length checks. This allows for unsafe memory copying operations that can lead to arbitrary memory corruption and possible code execution. Users are strongly advised to upgrade to version b5662 or later to mitigate these risks.

Human OS v1.0:
Ageing Is an Unpatched Zero-Day Vulnerability.

Remediate biological technical debt. Prime Ageing uses 95% high-purity SIRT6 activation to maintain genomic integrity and bolster systemic resilience.

Deploy the Patch

Affected Version(s)

llama.cpp < b5662

References

https://github.com/ggml-org/llama.cpp/security/advisories...
x_refsource_CONFIRM
https://github.com/ggml-org/llama.cpp/commit/3cfbbdb44e08...
x_refsource_MISC

CVSS V3.1

Score:
8.8
Severity:
HIGH
Confidentiality:
High
Integrity:
High
Availability:
High
Attack Vector:
Network
Attack Complexity:
Low
Privileges Required:
None
User Interaction:
Required
Scope:
Unchanged

Timeline

  • Vulnerability published

  • Vulnerability Reserved

JSON
.