EUVD-2026-69411
GHSA-jfjx-j76r-xrpf
Severity by source
AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N
CWE-617 causes process abort (A:H); no memory disclosure mechanism, so C:N; network-accessible file parser with no auth required.
Primary rating from Vendor (mitre).
CVSS VectorVendor: mitre
Lifecycle Timeline
5DescriptionCVE.org
llama.cpp b5693 and before has a Reachable Assertion via the gguf_reader::read function.
AnalysisAI
Reachable assertion in llama.cpp's GGUF file parser (gguf_reader::read) allows a remote unauthenticated attacker to crash the process by supplying a crafted GGUF model file to any service built on llama.cpp b5693 or earlier. CWE-617 (Reachable Assertion) causes process abort on assertion failure, making this effectively a denial-of-service primitive. …
Unlock full vulnerability intelligence
- Risk assessment & exploitation conditions
- Attack chain visualization
- Remediation with exact patch versions
- Threat intelligence from 22 sources
- Personal watchlist & email alerts
Free forever · No credit card required
Attack ChainAIDerived
Hypothetical attack flow derived from CVE metadata
Vulnerability AssessmentAI
| Exploitation | The target service must load attacker-supplied or attacker-influenced GGUF model files through gguf_reader::read. … Additional conditions and limiting factors are described in the full assessment. |
| Risk Assessment | The provided CVSS vector (AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N, score 7.5) assigns C:H and A:N, which is inconsistent with CWE-617 behavior. … Full risk analysis with EPSS, KEV, and SSVC signal comparison available after sign-in. |
| Exploit Scenario | Full exploit scenario with step-by-step reproduction available after sign-in. |
| Remediation | Update llama.cpp to any commit after b5693; no specific named patch release version was confirmed in the available references - consumers should pull HEAD or monitor https://github.com/ggml-org/llama.cpp for a tagged release that includes the assertion fix. … Detailed patch versions, workarounds, and compensating controls in full report. |
Recommended ActionAI
Within 24 hours, audit your infrastructure to identify any services running llama.cpp versions b5693 or earlier and assess the exposure (whether untrusted users can submit model files for processing). …
Sign in for detailed remediation steps and compensating controls.
Threat intelligence, references, and detailed analysis are available after sign-in.
Same weakness CWE-617 – Reachable Assertion
View allSame technique Denial Of Service
View allShare
External POC / Exploit Code
Leaving vuln.today