CVE-2026-78148

MEDIUMPre-NVD 5.35.3
EchelonGraph scoreMEDIUM confidence

“—” beside the score: it is equal to the CVSS score beside it.

Score 5.3 from GitHub Security Advisory published 2026-08-24. A secondary CVSS source baseline 5.3; sources differ by 0.0.

Triggered by: GitHub Security Advisory CVSS
Sources: EPSS, GitHub Security Advisory, a secondary CVSS source
Trending — 3 sources updated this week
5.3EG
EchelonGraph verdictMonitorRemediate within your standard update timelines at low or medium mission impact and sooner than that at high (the SSVC decision on this page).
  • Lower severity and no public exploit yet
CISA-KEV: Not listedEPSS PROB: 0.7%CVSS: 5.3Exploit: None knownExposed services: Not assessed

A fix is referenced (a reference tagged "Patch", often a source commit), but no release containing it is confirmed — find the release that contains it; until it is applied, mitigate (WAF / firewall / segmentation).

A vulnerability was determined in ggml-org llama.cpp bec4772f6. This affects the function rpc_server::graph_compute of the file ggml/src/ggml-rpc/ggml-rpc.cpp of the component ggml-RPC Server. Executing a manipulation can lead to null pointer dereference. The attack may be launched remotely. The pull request to fix this issue awaits acceptance.

CVSS v3
5.3
EG Score
5.3MEDIUMmedium confidence
EG Risk
39
EG Risk 39/100

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 computed (value × EchelonGraph’s weight)
Severity53% × 45%
The EG Score, 5.3 of 10.
Exploitation0.7% × 40%
FIRST EPSS: the 30-day exploitation probability when EchelonGraph scored this CVE.
Automatability100% × 15%
CISA's SSVC Automatable value: yes (Vulnrichment).
SSVC (CISA's decision table, applied by EchelonGraph): Track at low or medium mission impact; Attend at high (mission-essential systems).
Exploitation none (CISA Vulnrichment) · Automatable yes (CISA Vulnrichment) · Technical impact partial (CISA Vulnrichment). All three are CISA's SSVC values (Vulnrichment). EchelonGraph applied CISA's decision table to them; CISA publishes SSVC inputs and the table, not a decision for each CVE.
Action: A fix is referenced, but no release containing it is confirmed. Check the referenced fix and the vendor's advisory for a release that contains it and apply that within your standard update timelines at low or medium mission impact and sooner than that at high; until then, restrict network exposure of the affected system or apply the vendor's mitigation.
EPSS PROB
0.7%
EPSS %ILE
52nd
KEV
Not listed

SSVC (CISA's decision table, applied by EchelonGraph)Track at low or medium mission impact; Attend at high (mission-essential systems).

A fix is referenced, but no release containing it is confirmed. Check the referenced fix and the vendor's advisory for a release that contains it and apply that within your standard update timelines at low or medium mission impact and sooner than that at high; until then, restrict network exposure of the affected system or apply the vendor's mitigation.

Exploitation none (CISA Vulnrichment) · Automatable yes (CISA Vulnrichment) · Technical impact partial (CISA Vulnrichment). All three are CISA's SSVC values (Vulnrichment). EchelonGraph applied CISA's decision table to them; CISA publishes SSVC inputs and the table, not a decision for each CVE. Mission impact is CISA's Mission & Well-being decision point, and only you can judge it. CISA's table makes it high when Mission Prevalence is Essential — the vulnerable component "directly provides capabilities that constitute at least one MEF for at least one entity" (MEF: mission essential function) — or when Public Well-Being Impact is Irreversible: "multiple fatalities are likely", the cyber-physical system "is likely lost or destroyed", "extreme or serious externalities" are imposed on other parties, or social systems such as elections or the financial grid "are destabilized and potentially collapse". CISA's decision table

BOD 26-04 (CISA's remediation timeline, Table 1)14 days if the affected system is publicly exposed; 60 days if it is not.

In CISA KEV no (CISA's KEV catalog) · Automatable yes (CISA Vulnrichment) · Technical impact partial (CISA Vulnrichment). Whether your system is publicly exposed is yours to answer. BOD 26-04 binds US Federal Civilian Executive Branch agencies; for anyone else it is CISA's published timeline, a reference rather than an obligation. The directive · how EchelonGraph applies it

Published

August 23, 2026

Last Modified

October 12, 2026

Advisory Details (3)

Auto-updated Aug 23, 2026
Fix referenced — no release confirmed yet. Sources: github_pr.
Web page

GitHub - ggml-org/llama.cpp: LLM inference in C/C++ · GitHub

https://github.com/ggml-org/llama.cpp/
GitHub pull request

rpc : reject invalid top-level graph nodes in graph_compute

Upstream fix in progress (PR #25670 · ggml-org/llama.cpp, state=open)

https://github.com/ggml-org/llama.cpp/pull/25670
Web page

Remote unauthenticated NULL-pointer dereference in ggml-rpc graph_compute() via a node id of 0 (ggml_graph_plan/ggml_is_empty) · Issue #25299 · ggml-org/llama.cpp · GitHub

https://github.com/ggml-org/llama.cpp/issues/25299

Vendor Advisories for CVE-2026-78148(1)

These vendors published their own advisory mentioning this CVE — often with vendor-specific remediation steps + affected product lists not in NVD.

Affected Packages

(1 across 1 ecosystem)
Debian:14(1)
PackageVulnerable rangeFix by version rangeDependents
llama.cpp10108+dfsg-1 ... 9951+dfsg-3 (59 versions)
  • every version on: no fix on record
—

Weakness Classification(2)

MITRE Common Weakness Enumeration — the root-cause categories this CVE belongs to.

Data Freshness Timeline

(refreshed 18× in last 7d / 79× in last 30d)

Each row is a time one of our pipelines fetched, updated or re-scored this CVE. 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. An arrow marks a change the record states ("CVSS v3 → 9.1"); EPSS and GHSA rows show the values recorded at that time, not what changed (EPSS values are rounded; hover one for the exact figures). Most recent first.

Showing the most recent 98 of 141 refreshes on record for this CVE.

A repeat, a row identical to one the same pipeline wrote less than 10 seconds earlier, is not a separate refresh and is not counted. 2 repeat rows among the latest 100 are merged into the row they repeat. The 43 oldest rows on record are not shown and were not checked, so the counts can still include repeats.

  1. 2026-10-13 16:35 UTCEPSS rescoreEPSS 0.7% · 52nd percentile
  2. 2026-10-12 16:35 UTCEPSS rescoreEPSS 0.7% · 52nd percentile
  3. 2026-10-12 16:30 UTCGHSA enrichmentGHSA-7hmx-m2vh-6qvw · GitHub CVSS 5.3
  4. 2026-10-12 15:37 UTCEG score recompute
  5. 2026-10-11 19:23 UTCEG score recompute
  6. 2026-10-11 16:39 UTCEG score recompute
  7. 2026-10-11 13:57 UTCEG score recompute
  8. 2026-10-11 13:49 UTCEPSS rescoreEPSS 0.7% · 52nd percentile
  9. 2026-10-10 20:00 UTCEPSS rescoreEPSS 0.7% · 52nd percentile
  10. 2026-10-10 13:21 UTCEG score recompute
  11. 2026-10-10 13:20 UTCGHSA enrichmentGHSA-7hmx-m2vh-6qvw · GitHub CVSS 5.3
  12. 2026-10-09 20:07 UTCEPSS rescoreEPSS 0.7% · 52nd percentile
  13. 2026-10-09 06:19 UTCEG score recompute
  14. 2026-10-09 06:19 UTCGHSA enrichmentGHSA-7hmx-m2vh-6qvw · GitHub CVSS 5.3
  15. 2026-10-08 17:13 UTCEPSS rescoreEPSS 0.7% · 52nd percentile
  16. 2026-10-08 06:53 UTCEG score recompute
  17. 2026-10-08 06:52 UTCGHSA enrichmentGHSA-7hmx-m2vh-6qvw · GitHub CVSS 5.3
  18. 2026-10-07 23:48 UTCEPSS rescoreEPSS 0.7% · 52nd percentile
  19. 2026-10-07 07:17 UTCEG score recompute
  20. 2026-10-07 07:17 UTCGHSA enrichmentGHSA-7hmx-m2vh-6qvw · GitHub CVSS 5.3
  21. 2026-10-06 15:18 UTCEPSS rescoreEPSS 0.7% · 52nd percentile
  22. 2026-10-06 07:47 UTCEG score recompute
  23. 2026-10-06 07:47 UTCGHSA enrichmentGHSA-7hmx-m2vh-6qvw · GitHub CVSS 5.3
  24. 2026-10-05 17:43 UTCEPSS rescoreEPSS 0.7% · 52nd percentile
  25. 2026-10-05 05:09 UTCEG score recompute
Show 73 more
  1. 2026-10-05 05:09 UTCGHSA enrichmentGHSA-7hmx-m2vh-6qvw · GitHub CVSS 5.3
  2. 2026-10-04 23:22 UTCEPSS rescoreEPSS 0.7% · 52nd percentile
  3. 2026-10-04 05:44 UTCEG score recompute
  4. 2026-10-04 05:44 UTCGHSA enrichmentGHSA-7hmx-m2vh-6qvw · GitHub CVSS 5.3
  5. 2026-10-03 14:26 UTCEPSS rescoreEPSS 0.7% · 52nd percentile
  6. 2026-10-03 06:20 UTCEG score recompute
  7. 2026-10-03 06:20 UTCGHSA enrichmentGHSA-7hmx-m2vh-6qvw · GitHub CVSS 5.3
  8. 2026-10-02 06:44 UTCEG score recompute
  9. 2026-10-02 06:44 UTCGHSA enrichmentGHSA-7hmx-m2vh-6qvw · GitHub CVSS 5.3
  10. 2026-10-01 19:50 UTCEPSS rescoreEPSS 0.7% · 52nd percentile
  11. 2026-10-01 06:54 UTCEG score recompute
  12. 2026-10-01 06:53 UTCGHSA enrichmentGHSA-7hmx-m2vh-6qvw · GitHub CVSS 5.3
  13. 2026-09-30 07:21 UTCEG score recompute
  14. 2026-09-30 07:21 UTCGHSA enrichmentGHSA-7hmx-m2vh-6qvw · GitHub CVSS 5.3
  15. 2026-09-29 15:24 UTCEPSS rescoreEPSS 0.7% · 52nd percentile
  16. 2026-09-28 23:42 UTCEG score recompute
  17. 2026-09-28 23:42 UTCGHSA enrichmentGHSA-7hmx-m2vh-6qvw · GitHub CVSS 5.3
  18. 2026-09-28 13:52 UTCEPSS rescoreEPSS 0.7% · 52nd percentile
  19. 2026-09-28 00:16 UTCEG score recompute
  20. 2026-09-28 00:16 UTCGHSA enrichmentGHSA-7hmx-m2vh-6qvw · GitHub CVSS 5.3
  21. 2026-09-27 13:48 UTCEPSS rescoreEPSS 0.7% · 52nd percentile
  22. 2026-09-27 00:51 UTCEG score recompute
  23. 2026-09-27 00:51 UTCGHSA enrichmentGHSA-7hmx-m2vh-6qvw · GitHub CVSS 5.3
  24. 2026-09-26 15:59 UTCEPSS rescoreEPSS 0.7% · 52nd percentile
  25. 2026-09-26 00:28 UTCEPSS rescoreEPSS 0.7% · 52nd percentile
  26. 2026-09-24 19:24 UTCEG score recompute
  27. 2026-09-24 19:24 UTCGHSA enrichmentGHSA-7hmx-m2vh-6qvw · GitHub CVSS 5.3
  28. 2026-09-24 14:04 UTCEPSS rescoreEPSS 0.7% · 52nd percentile
  29. 2026-09-23 19:59 UTCEG score recompute
  30. 2026-09-23 19:59 UTCGHSA enrichmentGHSA-7hmx-m2vh-6qvw · GitHub CVSS 5.3
  31. 2026-09-23 17:54 UTCEPSS rescoreEPSS 0.5% · 44th percentile
  32. 2026-09-22 19:39 UTCEG score recompute
  33. 2026-09-22 19:39 UTCGHSA enrichmentGHSA-7hmx-m2vh-6qvw · GitHub CVSS 5.3
  34. 2026-09-22 16:01 UTCEPSS rescoreEPSS 0.5% · 44th percentile
  35. 2026-09-21 21:09 UTCEPSS rescoreEPSS 0.5% · 44th percentile
  36. 2026-09-21 19:53 UTCGHSA enrichmentGHSA-7hmx-m2vh-6qvw · GitHub CVSS 5.3
  37. 2026-09-20 20:28 UTCEG score recompute
  38. 2026-09-20 20:28 UTCGHSA enrichmentGHSA-7hmx-m2vh-6qvw · GitHub CVSS 5.3
  39. 2026-09-20 20:16 UTCEPSS rescoreEPSS 0.5% · 44th percentile
  40. 2026-09-19 21:04 UTCEG score recompute
  41. 2026-09-19 21:04 UTCGHSA enrichmentGHSA-7hmx-m2vh-6qvw · GitHub CVSS 5.3
  42. 2026-09-18 21:35 UTCEG score recompute
  43. 2026-09-18 21:35 UTCGHSA enrichmentGHSA-7hmx-m2vh-6qvw · GitHub CVSS 5.3
  44. 2026-09-18 19:28 UTCEPSS rescoreEPSS 0.5% · 44th percentile
  45. 2026-09-17 21:14 UTCEG score recompute
  46. 2026-09-17 21:14 UTCGHSA enrichmentGHSA-7hmx-m2vh-6qvw · GitHub CVSS 5.3
  47. 2026-09-16 21:36 UTCEG score recompute
  48. 2026-09-16 21:36 UTCGHSA enrichmentGHSA-7hmx-m2vh-6qvw · GitHub CVSS 5.3
  49. 2026-09-16 14:08 UTCEPSS rescoreEPSS 0.5% · 44th percentile
  50. 2026-09-16 05:15 UTCEPSS rescoreEPSS 0.5% · 43rd percentile
  51. 2026-09-15 21:40 UTCEG score recompute
  52. 2026-09-15 21:40 UTCGHSA enrichmentGHSA-7hmx-m2vh-6qvw · GitHub CVSS 5.3
  53. 2026-09-15 03:12 UTCEPSS rescoreEPSS 0.5% · 43rd percentile
  54. 2026-09-14 22:13 UTCGHSA enrichmentGHSA-7hmx-m2vh-6qvw · GitHub CVSS 5.3
  55. 2026-09-13 22:40 UTCEG score recompute
  56. 2026-09-13 22:40 UTCGHSA enrichmentGHSA-7hmx-m2vh-6qvw · GitHub CVSS 5.3
  57. 2026-09-12 23:15 UTCEG score recompute
  58. 2026-09-12 23:15 UTCGHSA enrichmentGHSA-7hmx-m2vh-6qvw · GitHub CVSS 5.3
  59. 2026-09-11 23:50 UTCEG score recompute
  60. 2026-09-11 23:50 UTCGHSA enrichmentGHSA-7hmx-m2vh-6qvw · GitHub CVSS 5.3
  61. 2026-09-11 14:53 UTCEPSS rescoreEPSS 0.5% · 43rd percentile
  62. 2026-09-11 00:25 UTCEG score recompute
  63. 2026-09-11 00:25 UTCGHSA enrichmentGHSA-7hmx-m2vh-6qvw · GitHub CVSS 5.3
  64. 2026-09-10 09:35 UTCEPSS rescoreEPSS 0.5% · 43rd percentile
  65. 2026-09-10 01:00 UTCGHSA enrichmentGHSA-7hmx-m2vh-6qvw · GitHub CVSS 5.3
  66. 2026-09-09 01:36 UTCEG score recompute
  67. 2026-09-09 01:36 UTCGHSA enrichmentGHSA-7hmx-m2vh-6qvw · GitHub CVSS 5.3
  68. 2026-09-08 22:01 UTCEPSS rescoreEPSS 0.5% · 43rd percentile
  69. 2026-09-07 15:24 UTCGHSA enrichmentGHSA-7hmx-m2vh-6qvw · GitHub CVSS 5.3
  70. 2026-09-06 14:29 UTCEG score recompute
  71. 2026-09-06 14:29 UTCGHSA enrichmentGHSA-7hmx-m2vh-6qvw · GitHub CVSS 5.3
  72. 2026-09-06 13:48 UTCEPSS rescoreEPSS 0.5% · 43rd percentile
  73. 2026-09-05 15:04 UTCGHSA enrichmentGHSA-7hmx-m2vh-6qvw · GitHub CVSS 5.3

Related CVEs(same product + same CWE)

Frequently asked(5)

What is CVE-2026-78148?
CVE-2026-78148 is a medium-severity vulnerability; its CVE record was published on August 23, 2026. A vulnerability was determined in ggml-org llama.cpp bec4772f6. This affects the function rpcserver::graphcompute of the file ggml/src/ggml-rpc/ggml-rpc.cpp of the component ggml-RPC Server. Executing a manipulation can lead to null pointer dereference. The attack may be launched remotely. The pull…
When was the CVE record for CVE-2026-78148 published?
The CVE record for CVE-2026-78148 was published on August 23, 2026. That is the record's publication date; the vulnerability itself may have been made public earlier. EchelonGraph's copy of the record carries a last-modified date of October 12, 2026; the record at its source may have been updated since.
Is CVE-2026-78148 actively exploited?
CVE-2026-78148 is not currently on CISA's Known Exploited Vulnerabilities catalog. FIRST EPSS estimates a 0.7% probability of exploitation in the next 30 days (52nd percentile of EPSS-scored CVEs).
What is the CVSS score of CVE-2026-78148?
CVE-2026-78148 has a CVSS base score of 5.3 (a secondary CVSS source that NVD displays; NVD's own analysis pending).
How do I remediate CVE-2026-78148?
A fix for CVE-2026-78148 is referenced (a reference tagged "Patch", often a source commit), but EchelonGraph has no release containing it on record. Check that reference and the vendor's advisory for a release that contains the fix and update to it; until then, restrict network exposure of the affected system or apply the vendor's mitigation. The vendor advisories EchelonGraph has for CVE-2026-78148 are linked in the Vendor Advisories panel on this page.

Dependency Blast Radius

See which npm, PyPI, Go, and Maven packages are affected by CVE-2026-78148

Explore →

Is Your Infrastructure Affected by CVE-2026-78148?

EchelonGraph automatically scans your cloud infrastructure and maps CVE exposure using blast radius analysis.

Book a Demo →Browse All CVEs