A vulnerability was determined in ggml-org llama.cpp bec4772f6. (CVE-2026-78148)
A medium severity vulnerability (CVE-2026-78148) exists in the ggml-org llama.cpp project affecting the rpc_server::graph_compute function in the ggml-RPC Server component. The issue is a null pointer dereference that can be triggered remotely, potentially causing a denial of service. A fix has been proposed but is not yet merged or officially released.
AI Analysis
Technical Summary
CVE-2026-78148 is a null pointer dereference vulnerability in the function rpc_server::graph_compute within the file ggml/src/ggml-rpc/ggml-rpc.cpp of the ggml-RPC Server component in the ggml-org llama.cpp project. This flaw can be exploited remotely by manipulating inputs to cause the server to dereference a null pointer, leading to a denial of service condition. The vulnerability has a CVSS 3.1 base score of 5.3 (medium severity) with network attack vector, low attack complexity, no privileges required, no user interaction, and impacts availability only. A pull request containing a fix is pending acceptance, indicating no official patch is currently available.
Potential Impact
Successful exploitation results in a denial of service via null pointer dereference, causing the affected service to crash or become unavailable. There is no impact on confidentiality or integrity according to the CVSS vector. The attack can be launched remotely without authentication or user interaction.
Mitigation Recommendations
No official patch or fix is currently available as the pull request to address the issue awaits acceptance. Users should monitor the ggml-org llama.cpp project repository or vendor advisories for the official fix and apply it promptly once released. Until then, consider limiting exposure of the ggml-RPC Server to untrusted networks to reduce risk.
A vulnerability was determined in ggml-org llama.cpp bec4772f6. (CVE-2026-78148)
Description
A medium severity vulnerability (CVE-2026-78148) exists in the ggml-org llama.cpp project affecting the rpc_server::graph_compute function in the ggml-RPC Server component. The issue is a null pointer dereference that can be triggered remotely, potentially causing a denial of service. A fix has been proposed but is not yet merged or officially released.
CVSS v3.1
Score 5.3medium
Weaknesses
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
CVE-2026-78148 is a null pointer dereference vulnerability in the function rpc_server::graph_compute within the file ggml/src/ggml-rpc/ggml-rpc.cpp of the ggml-RPC Server component in the ggml-org llama.cpp project. This flaw can be exploited remotely by manipulating inputs to cause the server to dereference a null pointer, leading to a denial of service condition. The vulnerability has a CVSS 3.1 base score of 5.3 (medium severity) with network attack vector, low attack complexity, no privileges required, no user interaction, and impacts availability only. A pull request containing a fix is pending acceptance, indicating no official patch is currently available.
Potential Impact
Successful exploitation results in a denial of service via null pointer dereference, causing the affected service to crash or become unavailable. There is no impact on confidentiality or integrity according to the CVSS vector. The attack can be launched remotely without authentication or user interaction.
Mitigation Recommendations
No official patch or fix is currently available as the pull request to address the issue awaits acceptance. Users should monitor the ggml-org llama.cpp project repository or vendor advisories for the official fix and apply it promptly once released. Until then, consider limiting exposure of the ggml-RPC Server to untrusted networks to reduce risk.
Technical Details
- Gcve Source
- db.gcve.eu
- Osv Id
- GHSA-7hmx-m2vh-6qvw
- Osv Schema Version
- 1.4.0
- Aliases
- ["CVE-2026-78148"]
- Ecosystems
- []
- Database Specific Severity
- MODERATE
- Cvss Version
- 3.1
Threat ID: 6a8c4c7dacd9273b499c104e
Added to database: 08/24/2026, 13:51:57 UTC
Last enriched: 08/24/2026, 14:32:29 UTC
Last updated: 08/24/2026, 14:52:02 UTC
Views: 4
Community Reviews
0 reviewsCrowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.
Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.
Actions
Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.
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
Check if your credentials are on the dark web
Instant breach scanning across billions of leaked records. Free tier available.