CVE-2026-86317

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 2026-09-07. 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

Also known asEUVD-2026-72459 (ENISA EUVD) · GHSA-c676-w283-jfxr (GitHub Security Advisories)Source: ENISA EUVD

5.3EG
EchelonGraph verdictMonitorNo fix is confirmed yet: check the vendor's advisory for a fixed release; until one is applied, restrict network exposure of the affected system or apply the vendor's mitigation on your normal schedule 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

No fix is confirmed yet — apply a workaround or compensating control (WAF / firewall / segmentation) and watch for the fix.

The CVE record's description, written by its CNA (VulDB), states the affected versions: "A vulnerability was detected in ggml-org llama.cpp up to 0.4.0." No release containing a fix is confirmed on record.

A vulnerability was detected in ggml-org llama.cpp up to 0.4.0. This impacts the function rpc_server::deserialize_tensor of the file ggml/src/ggml-rpc/ggml-rpc.cpp of the component RPC Server. Performing a manipulation of the argument ne results in reachable assertion. The attack is possible to be carried out remotely. The reported GitHub issue was closed automatically due to inactivity.

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 impact severity (EG Severity, the CVSS base score, never the KEV-floored or EPSS-lifted EG Score) with real-world exploitation and automatability, under weights EchelonGraph set by hand, so you can rank equal-severity CVEs and fix the most dangerous first. Higher = act sooner.

How it’s computed (value × EchelonGraph’s weight)
Severity53% × 45%
Impact severity (EG Severity): CVSS 5.3 of 10. Never the KEV-floored or EPSS-lifted EG Score.
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: No fix is confirmed yet. Check the vendor's advisory for a fixed release; until one is applied, restrict network exposure of the affected system or apply the vendor's mitigation on your normal schedule at low or medium mission impact and sooner than that at high.
EPSS PROB
0.7%
EPSS %ILE
53rd
KEV
Not listed

What the EG score is made of (scorer v4.0: the three questions the 0–10 score mixes, published apart · methodology)

The EG score (5.3): severity, escalated by confirmed exploitation. This CVE's 5.3 is its impact severity (EG Severity), not escalated.

EG Severity
5.3 MEDIUMCVSS-B, impact only: no KEV listing, EPSS or EG-KEV tier raises it.GitHub Security Advisory CVSS
EG Likelihood
0.7% within 30 daysSource: FIRST EPSS (model v2026.06.15, score date 2026-10-24). FIRST's exploitation probability, not an EchelonGraph model.
Confirmed exploitation
None on record (CISA KEV, EG-KEV Tier 1)Reported apart from the likelihood: an observed fact, not a probability.
EG Priority
SSVC Track at medium mission impactTrack at low or medium mission impact; Attend at high (mission-essential systems).CISA BOD 26-04: 14 days if the affected system is publicly exposed; 60 days if it is not.No released fix is confirmed on this page, but CISA's timeline does not wait for a fix's release: it starts when an agency identifies the flaw on an asset and updates the CDM Agency and Federal Dashboard, and the directive counts patching, decommissioning the system or another action as remediation. Until a fixed release is applied, mitigate as this page's verdict says.Each input and its source, and whom BOD 26-04 binds: the SSVC and BOD 26-04 blocks below.

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

No fix is confirmed yet. Check the vendor's advisory for a fixed release; until one is applied, restrict network exposure of the affected system or apply the vendor's mitigation on your normal schedule at low or medium mission impact and sooner than that at high.

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.

No released fix is confirmed on this page, but CISA's timeline does not wait for a fix's release: it starts when an agency identifies the flaw on an asset and updates the CDM Agency and Federal Dashboard, and the directive counts patching, decommissioning the system or another action as remediation. Until a fixed release is applied, mitigate as this page's verdict says.

The score's inputs: 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

September 7, 2026

Last Modified

September 8, 2026

Advisory Details (2)

Auto-updated Sep 7, 2026
No fix on record yet.
Web page

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

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

Remote unauthenticated DoS in ggml-rpc deserialize_tensor(): unvalidated tensor ne[0] aborts the server (SIGABRT) · Issue #25288 · ggml-org/llama.cpp · GitHub

https://github.com/ggml-org/llama.cpp/issues/25288

Vendor Advisories for CVE-2026-86317(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(1)

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

Data Freshness Timeline

(refreshed 8× in last 7d / 50× 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 100 of 124 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. None are among the latest 100 rows. The 24 oldest rows on record are not shown and were not checked, so the counts can still include repeats.

  1. 2026-11-01 16:35 UTCEPSS rescoreEPSS 0.7% · 53rd percentile
  2. 2026-10-31 16:33 UTCEPSS rescoreEPSS 0.7% · 53rd percentile
  3. 2026-10-30 16:35 UTCEPSS rescoreEPSS 0.7% · 53rd percentile
  4. 2026-10-29 23:55 UTCOSV refresh
  5. 2026-10-29 16:34 UTCEPSS rescoreEPSS 0.7% · 53rd percentile
  6. 2026-10-28 16:33 UTCEPSS rescoreEPSS 0.7% · 53rd percentile
  7. 2026-10-27 16:32 UTCEPSS rescoreEPSS 0.7% · 53rd percentile
  8. 2026-10-26 16:32 UTCEPSS rescoreEPSS 0.7% · 52nd percentile
  9. 2026-10-25 16:34 UTCEPSS rescoreEPSS 0.7% · 52nd percentile
  10. 2026-10-25 13:54 UTCEG score recompute
  11. 2026-10-24 16:34 UTCEPSS rescoreEPSS 0.7% · 52nd percentile
  12. 2026-10-23 16:32 UTCEPSS rescoreEPSS 0.7% · 52nd percentile
  13. 2026-10-22 16:35 UTCEPSS rescoreEPSS 0.7% · 52nd percentile
  14. 2026-10-22 12:46 UTCEG score recompute
  15. 2026-10-22 12:46 UTCGHSA enrichmentGHSA-c676-w283-jfxr · GitHub CVSS 5.3
  16. 2026-10-21 16:34 UTCEPSS rescoreEPSS 0.7% · 52nd percentile
  17. 2026-10-20 16:33 UTCEPSS rescoreEPSS 0.7% · 52nd percentile
  18. 2026-10-19 16:33 UTCEPSS rescoreEPSS 0.7% · 52nd percentile
  19. 2026-10-18 16:33 UTCEPSS rescoreEPSS 0.7% · 52nd percentile
  20. 2026-10-18 03:05 UTCEG score recompute
  21. 2026-10-17 16:35 UTCEPSS rescoreEPSS 0.7% · 52nd percentile
  22. 2026-10-16 16:44 UTCEPSS rescoreEPSS 0.7% · 52nd percentile
  23. 2026-10-15 16:33 UTCEPSS rescoreEPSS 0.7% · 52nd percentile
  24. 2026-10-14 16:34 UTCEPSS rescoreEPSS 0.7% · 52nd percentile
  25. 2026-10-13 16:35 UTCEPSS rescoreEPSS 0.7% · 51st percentile
Show 75 more
  1. 2026-10-12 16:35 UTCEPSS rescoreEPSS 0.7% · 51st percentile
  2. 2026-10-12 14:51 UTCEG score recompute
  3. 2026-10-11 19:17 UTCEG score recompute
  4. 2026-10-11 16:33 UTCEG score recompute
  5. 2026-10-11 13:51 UTCEG score recompute
  6. 2026-10-11 13:49 UTCEPSS rescoreEPSS 0.7% · 51st percentile
  7. 2026-10-10 20:00 UTCEPSS rescoreEPSS 0.7% · 51st percentile
  8. 2026-10-10 02:06 UTCEG score recompute
  9. 2026-10-10 02:06 UTCGHSA enrichmentGHSA-c676-w283-jfxr · GitHub CVSS 5.3
  10. 2026-10-09 20:07 UTCEPSS rescoreEPSS 0.7% · 51st percentile
  11. 2026-10-09 00:51 UTCEG score recompute
  12. 2026-10-09 00:51 UTCGHSA enrichmentGHSA-c676-w283-jfxr · GitHub CVSS 5.3
  13. 2026-10-08 17:13 UTCEPSS rescoreEPSS 0.7% · 51st percentile
  14. 2026-10-07 23:48 UTCEPSS rescoreEPSS 0.7% · 51st percentile
  15. 2026-10-07 13:16 UTCEG score recompute
  16. 2026-10-07 13:15 UTCGHSA enrichmentGHSA-c676-w283-jfxr · GitHub CVSS 5.3
  17. 2026-10-06 15:18 UTCEPSS rescoreEPSS 0.7% · 51st percentile
  18. 2026-10-06 10:54 UTCEG score recompute
  19. 2026-10-06 10:54 UTCGHSA enrichmentGHSA-c676-w283-jfxr · GitHub CVSS 5.3
  20. 2026-10-05 17:44 UTCEPSS rescoreEPSS 0.7% · 51st percentile
  21. 2026-10-05 09:30 UTCEG score recompute
  22. 2026-10-05 09:30 UTCGHSA enrichmentGHSA-c676-w283-jfxr · GitHub CVSS 5.3
  23. 2026-10-04 23:22 UTCEPSS rescoreEPSS 0.7% · 51st percentile
  24. 2026-10-04 08:19 UTCEG score recompute
  25. 2026-10-04 08:19 UTCGHSA enrichmentGHSA-c676-w283-jfxr · GitHub CVSS 5.3
  26. 2026-10-03 07:07 UTCEG score recompute
  27. 2026-10-03 07:07 UTCGHSA enrichmentGHSA-c676-w283-jfxr · GitHub CVSS 5.3
  28. 2026-10-02 17:57 UTCEPSS rescoreEPSS 0.7% · 51st percentile
  29. 2026-10-02 05:55 UTCEG score recompute
  30. 2026-10-02 05:55 UTCGHSA enrichmentGHSA-c676-w283-jfxr · GitHub CVSS 5.3
  31. 2026-10-01 19:50 UTCEPSS rescoreEPSS 0.7% · 51st percentile
  32. 2026-10-01 03:41 UTCEG score recompute
  33. 2026-10-01 03:41 UTCGHSA enrichmentGHSA-c676-w283-jfxr · GitHub CVSS 5.3
  34. 2026-09-30 15:04 UTCEPSS rescoreEPSS 0.7% · 51st percentile
  35. 2026-09-30 02:29 UTCEG score recompute
  36. 2026-09-30 02:29 UTCGHSA enrichmentGHSA-c676-w283-jfxr · GitHub CVSS 5.3
  37. 2026-09-28 15:43 UTCEG score recompute
  38. 2026-09-28 15:43 UTCGHSA enrichmentGHSA-c676-w283-jfxr · GitHub CVSS 5.3
  39. 2026-09-28 13:52 UTCEPSS rescoreEPSS 0.7% · 51st percentile
  40. 2026-09-27 14:14 UTCEG score recompute
  41. 2026-09-27 14:13 UTCGHSA enrichmentGHSA-c676-w283-jfxr · GitHub CVSS 5.3
  42. 2026-09-27 13:48 UTCEPSS rescoreEPSS 0.7% · 51st percentile
  43. 2026-09-26 15:59 UTCEPSS rescoreEPSS 0.7% · 51st percentile
  44. 2026-09-26 12:53 UTCEG score recompute
  45. 2026-09-26 12:53 UTCGHSA enrichmentGHSA-c676-w283-jfxr · GitHub CVSS 5.3
  46. 2026-09-25 11:42 UTCEG score recompute
  47. 2026-09-25 11:42 UTCGHSA enrichmentGHSA-c676-w283-jfxr · GitHub CVSS 5.3
  48. 2026-09-24 14:04 UTCEPSS rescoreEPSS 0.7% · 51st percentile
  49. 2026-09-24 10:20 UTCEG score recompute
  50. 2026-09-24 10:20 UTCGHSA enrichmentGHSA-c676-w283-jfxr · GitHub CVSS 5.3
  51. 2026-09-23 17:54 UTCEPSS rescoreEPSS 0.4% · 34th percentile
  52. 2026-09-23 09:08 UTCEG score recompute
  53. 2026-09-23 09:08 UTCGHSA enrichmentGHSA-c676-w283-jfxr · GitHub CVSS 5.3
  54. 2026-09-22 16:01 UTCEPSS rescoreEPSS 0.4% · 34th percentile
  55. 2026-09-22 07:55 UTCEG score recompute
  56. 2026-09-22 07:55 UTCGHSA enrichmentGHSA-c676-w283-jfxr · GitHub CVSS 5.3
  57. 2026-09-21 21:09 UTCEPSS rescoreEPSS 0.4% · 34th percentile
  58. 2026-09-21 06:43 UTCEG score recompute
  59. 2026-09-21 06:43 UTCGHSA enrichmentGHSA-c676-w283-jfxr · GitHub CVSS 5.3
  60. 2026-09-20 20:16 UTCEPSS rescoreEPSS 0.4% · 34th percentile
  61. 2026-09-20 05:31 UTCEG score recompute
  62. 2026-09-20 05:31 UTCGHSA enrichmentGHSA-c676-w283-jfxr · GitHub CVSS 5.3
  63. 2026-09-19 04:19 UTCEG score recompute
  64. 2026-09-19 04:19 UTCGHSA enrichmentGHSA-c676-w283-jfxr · GitHub CVSS 5.3
  65. 2026-09-18 19:28 UTCEPSS rescoreEPSS 0.4% · 34th percentile
  66. 2026-09-18 03:07 UTCEG score recompute
  67. 2026-09-18 03:07 UTCGHSA enrichmentGHSA-c676-w283-jfxr · GitHub CVSS 5.3
  68. 2026-09-17 19:32 UTCEPSS rescoreEPSS 0.4% · 34th percentile
  69. 2026-09-17 01:55 UTCEG score recompute
  70. 2026-09-17 01:55 UTCGHSA enrichmentGHSA-c676-w283-jfxr · GitHub CVSS 5.3
  71. 2026-09-16 14:09 UTCEPSS rescoreEPSS 0.4% · 34th percentile
  72. 2026-09-16 05:15 UTCEPSS rescoreEPSS 0.4% · 34th percentile
  73. 2026-09-16 00:43 UTCEG score recompute
  74. 2026-09-16 00:43 UTCGHSA enrichmentGHSA-c676-w283-jfxr · GitHub CVSS 5.3
  75. 2026-09-15 03:12 UTCEPSS rescoreEPSS 0.4% · 34th percentile

Frequently asked(5)

What is CVE-2026-86317?
CVE-2026-86317 is a medium-severity vulnerability; its CVE record was published on September 7, 2026. A vulnerability was detected in ggml-org llama.cpp up to 0.4.0. This impacts the function rpc_server::deserialize_tensor of the file ggml/src/ggml-rpc/ggml-rpc.cpp of the component RPC Server. Performing a manipulation of the argument ne results in reachable assertion. The attack is possible to be…
When was the CVE record for CVE-2026-86317 published?
The CVE record for CVE-2026-86317 was published on September 7, 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 September 8, 2026; the record at its source may have been updated since.
Is CVE-2026-86317 actively exploited?
CVE-2026-86317 is not currently on CISA's Known Exploited Vulnerabilities catalog. FIRST EPSS estimates a 0.7% probability of exploitation in the next 30 days (53rd percentile of EPSS-scored CVEs).
What is the CVSS score of CVE-2026-86317?
CVE-2026-86317 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-2026-86317?
No fix for CVE-2026-86317 is confirmed yet. Until one is published, restrict network exposure of the affected system or apply the vendor's mitigation — for example, keep it off the internet or limit it to trusted networks — and watch the vendor's advisory for the fix. The CVE record's description, written by its CNA (VulDB), states the affected versions: "A vulnerability was detected in ggml-org llama.cpp up to 0.4.0." No release containing a fix is confirmed on record. The vendor advisories EchelonGraph has for CVE-2026-86317 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-2026-86317

Explore →

Is Your Infrastructure Affected by CVE-2026-86317?

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