CVE-2026-110810: Out-of-Bounds Read in ggml-org whisper.cpp
Description
CVE-2026-110810 is an out-of-bounds read vulnerability in the whisper_model_load function of the ggml-org whisper.cpp component, affecting versions 1.9.0 through 1.9.4. The flaw arises from manipulation of the argument ttype and requires local access to exploit. A public exploit exists. The vendor has released version 1.9.5 to address this issue.
CVSS v4.0
Score 2.4low
Affected software
ggml-org
whisper.cpp
pkg:github/ggml-org/whisper.cppcpe:2.3:a:ggml-org:whisper.cpp:*:*:*:*:*:*:*:*Run on your own infrastructure? Check whether these packages are installed with threat-finder — our free open-source scanner.
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
This vulnerability in ggml-org whisper.cpp up to version 1.9.4 involves an out-of-bounds read triggered by manipulating the argument ttype in the whisper_model_load function within src/whisper.cpp. Exploitation requires local privileges and user interaction. The vendor responded promptly and released a patch in version 1.9.5 (commit 60c0be6ac8fa71b1a2ae2dd938a31a34a508e774) to fix the issue. The CVSS 4.0 base score is 2.4, indicating low severity.
Potential Impact
The vulnerability allows a local attacker with low privileges to cause an out-of-bounds read, which may lead to information disclosure or application instability. The impact is limited due to the requirement for local access and user interaction. No evidence of widespread exploitation in the wild is reported.
Mitigation Recommendations
Upgrade to ggml-org whisper.cpp version 1.9.5 or later, which contains the official fix for this vulnerability. No additional mitigation steps are required as the patch fully addresses the issue.
Technical Details
- Data Version
- 5.2
- Assigner Short Name
- VulDB
- Date Reserved
- 2026-10-14T18:24:32.712Z
- Cvss Version
- 4.0
- State
- PUBLISHED
Threat ID: 6ad01bf62cdf04f656bf3e42
Added to database: 10/15/2026, 00:19:02 UTC
Last enriched: 10/15/2026, 00:33:15 UTC
Last updated: 10/15/2026, 00:33:53 UTC
Views: 5
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.