A flaw has been found in ggml-org llama.cpp e15efe0. This vulnerability affects the function transform of the file common/json-schema-to-grammar.cpp of the component JSON-Schema-to-GBNF Conversion. This manipulation causes allocation of resources. The attack may be initiated remotely. The pull request to fix this issue awaits acceptance.
CVE-2026-17501
Score 5.3 from GitHub Security Advisory published 2026-07-27. a secondary CVSS source baseline 5.3; sources differ by 0.0.
- Lower severity and no public exploit yet
No vendor fix yet — apply a workaround or compensating control (WAF / firewall / segmentation) and watch for a patch.
- CVSS v3
- 5.3
- EG Score
- 5.3(high)
- EG Risk
- 28(Track)EG Risk 28/100SSVC: Track
EG Risk is EchelonGraph's 0–100 priority score: it fuses intrinsic severity with real-world exploitation and automatability so you can rank equal-severity CVEs and fix the most dangerous first. Higher = act sooner. Distinct from the 0–10 EG Score (severity).
How it’s computedSeverity53% × 45%Exploitation0% × 40%Automatability30% × 15%Action: Routine — remediate on your standard cadence. - EPSS PROB
- —
- EPSS %ILE
- —
- KEV
- Not listed
Published
July 27, 2026
Last Modified
July 27, 2026
Advisory Details (3)
Auto-updated Jul 27, 2026GitHub - ggml-org/llama.cpp: LLM inference in C/C++ · GitHub
https://github.com/ggml-org/llama.cpp/json-schema-to-grammar: harden _visit_pattern against malformed regex patterns
Upstream fix in progress (PR #25308 · ggml-org/llama.cpp, state=open)
https://github.com/ggml-org/llama.cpp/pull/25308Stack overflow (uncontrolled recursion) in JSON-Schema-to-GBNF conversion on a deeply nested schema · Issue #25283 · ggml-org/llama.cpp · GitHub
https://github.com/ggml-org/llama.cpp/issues/25283Vendor Advisories for CVE-2026-17501(1)
These vendors published their own advisory mentioning this CVE — often with vendor-specific remediation steps + affected product lists not in NVD.
Weakness Classification(2)
MITRE Common Weakness Enumeration — the root-cause categories this CVE belongs to.
Data Freshness Timeline
(refreshed 5× in last 7d / 5× in last 30d)
Each row is a source pipeline that fetched or updated this CVE on that date, with what changed. For example, "NVD update" means NVD published or revised its analysis for this CVE; "MITRE cvelistV5" means we ingested or refreshed it from the CNA feed. Most recent first.
- 2026-07-27 20:43 UTCEG score recompute
- 2026-07-27 20:43 UTCGHSA enrichment
- 2026-07-27 01:23 UTCEG score recompute
- 2026-07-27 01:02 UTCEG score recompute
- 2026-07-27 01:02 UTCMITRE cvelistV5first tracked
Related CVEs(same CWE)
Same CWE
10 shownCWE-400 · CWE-770
- CVE-2004-1464NVD 5.9EG 9.0 KEVEPSS p92CRITICAL
- CVE-2010-3705EG 8.3HIGH
- CVE-2006-1364NVD 7.5EG 8.2EPSS p99HIGH
- CVE-2008-5180NVD 5.3EG 7.9EPSS p99HIGH
- CVE-2012-0024EG 7.8HIGH
- CVE-2011-3192EG 7.8EPSS p100HIGH
- CVE-2010-4686EG 7.8HIGH
- CVE-2010-4671EG 7.8HIGH
- CVE-2009-2054EG 7.8HIGH
- CVE-2009-2726EG 7.8EPSS p93HIGH
Frequently asked(4)
What is CVE-2026-17501?
When was CVE-2026-17501 disclosed?
What is the CVSS score of CVE-2026-17501?
How do I remediate CVE-2026-17501?
Dependency Blast Radius
Explore the affected products and dependency analysis for CVE-2026-17501
Is Your Infrastructure Affected by CVE-2026-17501?
EchelonGraph automatically scans your cloud infrastructure and maps CVE exposure using blast radius analysis.