Skip to main content

llama.cpp CVE-2026-52130

| EUVDEUVD-2026-69412 HIGH
Uncontrolled Recursion (CWE-674)
2026-09-01 mitre GHSA-8q78-m7w9-j45m
7.5
CVSS 3.1 · Vendor: mitre
Share

Severity by source

Vendor (mitre) PRIMARY
7.5 HIGH
AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
vuln.today AI
7.5 HIGH

Network-reachable endpoint requires no authentication; only availability is impacted via stack exhaustion with no confidentiality or integrity loss.

3.1 AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
4.0 AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N

Primary rating from Vendor (mitre).

CVSS VectorVendor: mitre

Attack Vector
Network
Attack Complexity
Low
Privileges Required
None
User Interaction
None
Scope
Unchanged
Confidentiality
None
Integrity
None
Availability
High

Lifecycle Timeline

5
Metadata Corrected
Sep 01, 2026 - 20:40 vuln.today
tag: N A removed
Analysis Generated
Sep 01, 2026 - 20:06 vuln.today
CVSS changed
Sep 01, 2026 - 19:22 NVD
7.5 (HIGH)
CVE Published
Sep 01, 2026 - 00:00 cve.org
HIGH 7.5
CVE Published
Sep 01, 2026 - 00:00 cve.org
UNKNOWN (no severity yet)

DescriptionCVE.org

llama.cpp b5693 and before is vulnerable to Uncontrolled Recursion in common/json-schema-to-grammar.cpp, resulting in a denial of service.

AnalysisAI

Uncontrolled recursion in llama.cpp's JSON-schema-to-grammar converter (common/json-schema-to-grammar.cpp, versions through build b5693) allows a remote unauthenticated attacker to crash the service by submitting a crafted JSON schema that triggers unbounded recursive processing, exhausting the call stack and producing a denial of service. The CVSS vector confirms network reachability with no authentication required and no user interaction needed, making this exploitable against any deployment that exposes the llama.cpp HTTP server endpoint to untrusted clients. …

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

Access
technique details hidden
Delivery
technique details hidden
Exploit
technique details hidden
Execution
technique details hidden
Impact
technique details hidden

Vulnerability AssessmentAI

Exploitation The llama.cpp HTTP server must be running and its structured-output grammar endpoint must be reachable by the attacker. … Additional conditions and limiting factors are described in the full assessment.
Risk Assessment The CVSS 3.1 score of 7.5 (AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H) is well-calibrated for this vulnerability: network-reachable, trivially triggered, no privileges needed, with full availability loss but no confidentiality or integrity impact. … 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 a build later than b5693; monitor https://github.com/ggml-org/llama.cpp for the specific commit or tagged release that addresses this issue, as no exact patched version was independently confirmed from available data. … Detailed patch versions, workarounds, and compensating controls in full report.

Recommended ActionAI

Within 24 hours, inventory all llama.cpp deployments through build b5693 and determine which have HTTP server endpoints accessible from untrusted networks. …

Sign in for detailed remediation steps and compensating controls.

Threat intelligence, references, and detailed analysis are available after sign-in.

Share

CVE-2026-52130 vulnerability details – vuln.today

This site uses cookies essential for authentication and security. No tracking or analytics cookies are used. Privacy Policy