Skip to main content
EPSS 0.6%top 55%

CVE-2026-78147: Deserialization in ggml-org llama.cpp

0
Medium
VulnerabilityCVE-2026-78147cvecve-2026-78147
Published: 08/23/2026 (08/23/2026, 23:00:13 UTC)
Source: CVE Database V5
Vendor/Project: ggml-org
Product: llama.cpp

Description

CVE-2026-78147 is a medium severity deserialization vulnerability in the ggml-org llama.cpp project. It affects the deserialize_tensor function in the ggml-RPC Server component. The flaw allows remote attackers to manipulate the op/op_params arguments during deserialization. This vulnerability is distinct from a prior issue (CVE-2026-34159) and was reported but closed due to inactivity. No patch or remediation information is currently available.

CVSS v4.0

Score 6.9medium

Attack Vector
Network
Attack Complexity
Low
Attack Requirements
None
Privileges Required
None
User Interaction
None
Vuln. Confidentiality
Low
Vuln. Integrity
Low
Vuln. Availability
Low
Subsq. Confidentiality
None
Subsq. Integrity
None
Subsq. Availability
None
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N/E:X

Affected software

ggml-org

llama.cpp

CPE configurations
cpe:2.3:a:ggml-org:llama.cpp:*:*:*:*:*:*:*:*

AI-Powered Analysis

Machine-generated threat intelligence

AILast updated: 09/10/2026, 23:18:15 UTC

Technical Analysis

The vulnerability exists in the deserialize_tensor function within ggml/src/ggml-rpc/ggml-rpc.cpp of the ggml-RPC Server component in the ggml-org llama.cpp project. An attacker can remotely manipulate the op/op_params arguments during deserialization, potentially leading to security issues. This vulnerability differs from CVE-2026-34159, which only added a buffer==nullptr rejection in create_node() but did not validate op or op_params. The issue was reported but the GitHub issue was closed automatically due to inactivity. No known exploits are reported in the wild.

Potential Impact

The vulnerability allows remote attackers to manipulate deserialization parameters, which may lead to partial compromise of confidentiality, integrity, and availability as indicated by the CVSS vector (VC:L, VI:L, VA:L). The attack requires no privileges and no user interaction. The overall CVSS score is 6.9 (medium severity).

Mitigation Recommendations

Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. Since the GitHub issue was closed due to inactivity and no patch or fix links are provided, users should monitor official ggml-org llama.cpp channels for updates. No official fix or temporary workaround is currently documented.

Pro Console: star threats, build custom feeds, automate alerts via Slack, email & webhooks.Upgrade to Pro

Technical Details

Data Version
5.2
Assigner Short Name
VulDB
Date Reserved
2026-08-23T06:39:05.390Z
Cvss Version
4.0
State
PUBLISHED

Threat ID: 6a8b80d0acd9273b4982ddb8

Added to database: 08/23/2026, 23:22:56 UTC

Last enriched: 09/10/2026, 23:18:15 UTC

Last updated: 10/06/2026, 18:48:25 UTC

Views: 86

Community Reviews

0 reviews

Crowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.

Sort by
Loading community insights…

Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.

Actions

PRO

Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.

Please log in to the Console to use AI analysis features.

Need more coverage?

Upgrade to Pro Console for AI refresh and higher limits.

For incident response and remediation, OffSeq services can help resolve threats faster.

Latest Threats

Breach by OffSeqOFFSEQFRIENDS — 25% OFF

Check if your credentials are on the dark web

Instant breach scanning across billions of leaked records. Free tier available.

Scan now
OffSeq TrainingCredly Certified

Lead Pen Test Professional

Technical5-day eLearningPECB Accredited
View courses