CVE-2026-7482

CRITICALNVD 9.19.1
EchelonGraph scoreMEDIUM confidence

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

This critical-severity CVE scores 9.1 under NVD CVSS v3. EPSS exploit probability: 2.2% (82nd percentile of EPSS-scored CVEs). No GitHub Security Advisory CVSS is on record for this CVE.

Triggered by: Headline CVSS from NVD CVSS v3
Sources: EPSS, NVD CVSS v3
Elevated

Also known asEUVD-2026-26949 (ENISA EUVD)Source: ENISA EUVD

9.1EG
EchelonGraph verdictPlan a fixRemediate within your standard update timelines at low or medium mission impact and sooner than that at high (the SSVC decision on this page).
  • Public exploit or proof-of-concept code is available
CISA-KEV: Not listedEPSS PROB: 2.2%CVSS: 9.1Exploit: Public PoCExposed services: Not assessed

A fix is available — apply it.

Fixed versions, as the CVE record's CNA (Echo Software Ltd.) states them: "Upgrade to ollama 0.17.1 or later."

Ollama before 0.17.1 contains a heap out-of-bounds read vulnerability in the GGUF model loader. The /api/create endpoint accepts an attacker-supplied GGUF file in which the declared tensor offset and size exceed the file's actual length; during quantization in fs/ggml/gguf.go and server/quantization.go (WriteTo()), the server reads past the allocated heap buffer. The leaked memory contents may include environment variables, API keys, system prompts, and concurrent users' conversation data, and can be exfiltrated by uploading the resulting model artifact through the /api/push endpoint to an attacker-controlled registry. The /api/create and /api/push endpoints have no authentication in the upstream distribution. Default deployments bind to 127.0.0.1, but the documented OLLAMA_HOST=0.0.0.0 configuration is widely used in practice (large public-internet exposure observed).

CVSS v3
9.1
EG Score
9.1CRITICALmedium confidence
EG Risk
72
EG Risk 72/100

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)
Severity91% × 45%
Impact severity (EG Severity): CVSS 9.1 of 10. Never the KEV-floored or EPSS-lifted EG Score.
Exploitation40% × 40%
EchelonGraph's fixed weight for EG-KEV Tier 3 (Elevated): a constant, not a probability.
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 total (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 available. Apply it within your standard update timelines at low or medium mission impact and sooner than that at high.
EPSS PROB
2.2%
EPSS %ILE
82nd
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 (9.1): severity, escalated by confirmed exploitation. This CVE's 9.1 is its impact severity (EG Severity), not escalated.

EG Severity
9.1 CRITICALCVSS-B, impact only: no KEV listing, EPSS or EG-KEV tier raises it.NVD CVSS v3 · CVSS v3.0 or v3.1
EG Likelihood
2.2% within 30 daysSource: FIRST EPSS (model v2026.06.15, score date 2026-10-29). 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: 3 days if the affected system is publicly exposed; 60 days if it is not.Each input and its source: 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).

A fix is available. Apply it within your standard update timelines at low or medium mission impact and sooner than that at high.

Exploitation none (CISA Vulnrichment) · Automatable yes (CISA Vulnrichment) · Technical impact total (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)3 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 total (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

May 4, 2026

Last Modified

May 11, 2026

Advisory Details (3)

Auto-updated Aug 1, 2026
Patch available. Sources: github_commit, github_pr, github_release.
GitHub release Patch Available

v0.17.1

Patch available: ollama/ollama v0.17.1

https://github.com/ollama/ollama/releases/tag/v0.17.1
GitHub pull request

ggml: ensure tensor size is valid

Fix merged in ollama/ollama PR #14406 on 2026-02-25 — awaiting tagged release

https://github.com/ollama/ollama/pull/14406
GitHub commit

commit 88d57d0483cc (ollama/ollama)

Fix landed in ollama/ollama commit 88d57d0483cc — awaiting tagged release

https://github.com/ollama/ollama/commit/88d57d0483cca907e0b23a968c83627a20b21047

Affected Packages

(1 across 1 ecosystem)
Go(1)
PackageVulnerable rangeFix by version rangeDependents
github.com/ollama/ollama—
  • every version up to 0.17.1: fixed in 0.17.1
—

Weakness Classification(1)

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

Data Freshness Timeline

(refreshed 15× in last 7d / 52× 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 94 of 210 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. 6 repeat rows among the latest 100 are merged into the row they repeat. The 116 oldest rows on record are not shown and were not checked, so the counts can still include repeats.

  1. 2026-10-30 15:02 UTCEG score recompute
  2. 2026-10-29 16:34 UTCEPSS rescoreEPSS 2.2% · 82nd percentile
  3. 2026-10-29 13:31 UTCEG score recompute
  4. 2026-10-28 16:33 UTCEPSS rescoreEPSS 2.2% · 82nd percentile
  5. 2026-10-28 11:59 UTCEG score recompute
  6. 2026-10-27 16:32 UTCEPSS rescoreEPSS 2.2% · 82nd percentile
  7. 2026-10-27 10:27 UTCEG score recompute
  8. 2026-10-26 16:32 UTCEPSS rescoreEPSS 2.2% · 82nd percentile
  9. 2026-10-26 08:56 UTCEG score recompute
  10. 2026-10-25 16:34 UTCEPSS rescoreEPSS 2.2% · 82nd percentile
  11. 2026-10-25 14:03 UTCEG score recompute
  12. 2026-10-25 07:25 UTCEG score recompute
  13. 2026-10-24 16:33 UTCEPSS rescoreEPSS 0.7% · 53rd percentile
  14. 2026-10-24 05:53 UTCEG score recompute
  15. 2026-10-23 16:32 UTCEPSS rescoreEPSS 0.7% · 53rd percentile
  16. 2026-10-23 04:18 UTCEG score recompute
  17. 2026-10-22 16:35 UTCEPSS rescoreEPSS 0.7% · 53rd percentile
  18. 2026-10-22 02:44 UTCEG score recompute
  19. 2026-10-21 16:33 UTCEPSS rescoreEPSS 0.7% · 53rd percentile
  20. 2026-10-21 01:09 UTCEG score recompute
  21. 2026-10-20 16:33 UTCEPSS rescoreEPSS 0.7% · 52nd percentile
  22. 2026-10-19 23:34 UTCEG score recompute
  23. 2026-10-19 16:33 UTCEPSS rescoreEPSS 0.7% · 52nd percentile
  24. 2026-10-18 22:01 UTCEG score recompute
  25. 2026-10-18 16:33 UTCEPSS rescoreEPSS 0.7% · 52nd percentile
Show 69 more
  1. 2026-10-18 03:14 UTCEG score recompute
  2. 2026-10-17 20:01 UTCEG score recompute
  3. 2026-10-17 16:35 UTCEPSS rescoreEPSS 0.7% · 52nd percentile
  4. 2026-10-16 18:28 UTCEG score recompute
  5. 2026-10-16 16:44 UTCEPSS rescoreEPSS 0.7% · 52nd percentile
  6. 2026-10-15 16:33 UTCEPSS rescoreEPSS 0.7% · 52nd percentile
  7. 2026-10-15 15:09 UTCEG score recompute
  8. 2026-10-14 16:33 UTCEPSS rescoreEPSS 0.7% · 52nd percentile
  9. 2026-10-14 09:32 UTCEG score recompute
  10. 2026-10-13 16:35 UTCEPSS rescoreEPSS 0.7% · 52nd percentile
  11. 2026-10-13 07:11 UTCEG score recompute
  12. 2026-10-12 16:35 UTCEPSS rescoreEPSS 0.7% · 52nd percentile
  13. 2026-10-12 15:39 UTCEG score recompute
  14. 2026-10-11 19:25 UTCEG score recompute
  15. 2026-10-11 16:41 UTCEG score recompute
  16. 2026-10-11 14:00 UTCEG score recompute
  17. 2026-10-11 13:49 UTCEPSS rescoreEPSS 0.7% · 52nd percentile
  18. 2026-10-10 20:00 UTCEPSS rescoreEPSS 0.7% · 52nd percentile
  19. 2026-10-09 20:07 UTCEPSS rescoreEPSS 0.7% · 52nd percentile
  20. 2026-10-08 17:13 UTCEPSS rescoreEPSS 0.7% · 52nd percentile
  21. 2026-10-07 23:48 UTCEPSS rescoreEPSS 0.7% · 52nd percentile
  22. 2026-10-06 15:18 UTCEPSS rescoreEPSS 0.7% · 52nd percentile
  23. 2026-10-05 17:43 UTCEPSS rescoreEPSS 0.7% · 52nd percentile
  24. 2026-10-04 23:22 UTCEPSS rescoreEPSS 0.7% · 52nd percentile
  25. 2026-10-03 14:26 UTCEPSS rescoreEPSS 0.7% · 52nd percentile
  26. 2026-10-02 17:57 UTCEPSS rescoreEPSS 0.7% · 51st percentile
  27. 2026-10-01 19:50 UTCEPSS rescoreEPSS 0.7% · 51st percentile
  28. 2026-09-30 11:17 UTCOSV refresh
  29. 2026-09-29 15:24 UTCEPSS rescoreEPSS 0.7% · 51st percentile
  30. 2026-09-28 13:52 UTCEPSS rescoreEPSS 0.7% · 51st percentile
  31. 2026-09-27 13:48 UTCEPSS rescoreEPSS 0.7% · 51st percentile
  32. 2026-09-26 15:59 UTCEPSS rescoreEPSS 0.7% · 51st percentile
  33. 2026-09-26 00:28 UTCEPSS rescoreEPSS 0.7% · 51st percentile
  34. 2026-09-24 14:04 UTCEPSS rescoreEPSS 0.7% · 51st percentile
  35. 2026-09-23 17:54 UTCEPSS rescoreEPSS 2.2% · 82nd percentile
  36. 2026-09-22 16:01 UTCEPSS rescoreEPSS 2.2% · 82nd percentile
  37. 2026-09-21 21:09 UTCEPSS rescoreEPSS 2.2% · 81st percentile
  38. 2026-09-20 20:16 UTCEPSS rescoreEPSS 2.2% · 82nd percentile
  39. 2026-09-18 19:28 UTCEPSS rescoreEPSS 2.2% · 82nd percentile
  40. 2026-09-16 14:08 UTCEPSS rescoreEPSS 2.2% · 81st percentile
  41. 2026-09-16 05:15 UTCEPSS rescoreEPSS 2.2% · 81st percentile
  42. 2026-09-15 03:12 UTCEPSS rescoreEPSS 2.2% · 81st percentile
  43. 2026-09-11 18:10 UTCOSV refresh
  44. 2026-09-11 14:53 UTCEPSS rescoreEPSS 2.2% · 81st percentile
  45. 2026-09-08 22:01 UTCEPSS rescoreEPSS 2.2% · 81st percentile
  46. 2026-09-06 13:48 UTCEPSS rescoreEPSS 2.2% · 81st percentile
  47. 2026-09-04 05:07 UTCEPSS rescoreEPSS 2.2% · 81st percentile
  48. 2026-09-02 14:12 UTCEPSS rescoreEPSS 2.2% · 81st percentile
  49. 2026-09-01 13:54 UTCEPSS rescoreEPSS 2.2% · 81st percentile
  50. 2026-09-01 04:40 UTCEPSS rescoreEPSS 2.2% · 81st percentile
  51. 2026-08-30 19:17 UTCEPSS rescoreEPSS 2.2% · 81st percentile
  52. 2026-08-30 01:22 UTCEPSS rescoreEPSS 2.2% · 81st percentile
  53. 2026-08-28 21:42 UTCEPSS rescoreEPSS 2.2% · 81st percentile
  54. 2026-08-27 14:25 UTCEPSS rescoreEPSS 2.2% · 81st percentile
  55. 2026-08-26 14:47 UTCEPSS rescoreEPSS 2.2% · 81st percentile
  56. 2026-08-25 13:49 UTCEPSS rescoreEPSS 2.2% · 81st percentile
  57. 2026-08-24 14:18 UTCEPSS rescoreEPSS 2.2% · 81st percentile
  58. 2026-08-23 21:36 UTCEG score recompute
  59. 2026-08-23 00:19 UTCEPSS rescoreEPSS 1.9% · 78th percentile
  60. 2026-08-21 23:49 UTCEPSS rescoreEPSS 1.9% · 78th percentile
  61. 2026-08-20 22:56 UTCEPSS rescoreEPSS 1.9% · 78th percentile
  62. 2026-08-19 17:04 UTCEPSS rescoreEPSS 1.9% · 78th percentile
  63. 2026-08-18 13:49 UTCEPSS rescoreEPSS 1.9% · 78th percentile
  64. 2026-08-17 13:47 UTCEPSS rescoreEPSS 1.9% · 78th percentile
  65. 2026-08-17 13:13 UTCEG score recompute
  66. 2026-08-16 14:56 UTCEPSS rescoreEPSS 1.9% · 78th percentile
  67. 2026-08-16 05:04 UTCEG score recompute
  68. 2026-08-16 02:15 UTCEPSS rescoreEPSS 1.9% · 78th percentile
  69. 2026-08-15 01:31 UTCEPSS rescoreEPSS 1.9% · 78th percentile

Publicly available exploits

(1 reference)

Public exploit code is referenced for this CVE (1 GitHub PoC). Defenders should treat patch urgency accordingly.

  • GitHub PoC0x0OZ/CVE-2026-7482-PoC
    Published May 5, 2026

    1day vuln research I guess

    Open source ↗

Related CVEs(same product + same CWE)

Frequently asked(5)

What is CVE-2026-7482?
CVE-2026-7482 is a critical-severity vulnerability; its CVE record was published on May 4, 2026. Ollama before 0.17.1 contains a heap out-of-bounds read vulnerability in the GGUF model loader. The /api/create endpoint accepts an attacker-supplied GGUF file in which the declared tensor offset and size exceed the file's actual length; during quantization in fs/ggml/gguf.go and…
When was CVE-2026-7482 made public?
CVE-2026-7482 was made public on February 25, 2026: that is the date its CVE record's CNA, Echo Software Ltd., gives for when the vulnerability was made public. The CVE record itself was published on May 4, 2026. EchelonGraph's copy of the record carries a last-modified date of May 11, 2026; the record at its source may have been updated since.
Is CVE-2026-7482 actively exploited?
CVE-2026-7482 is not currently on CISA's Known Exploited Vulnerabilities catalog. FIRST EPSS estimates a 2.2% probability of exploitation in the next 30 days (82nd percentile of EPSS-scored CVEs).
What is the CVSS score of CVE-2026-7482?
CVE-2026-7482 has a CVSS v3 base score of 9.1 (NVD).
How do I remediate CVE-2026-7482?
A fix for CVE-2026-7482 is available: update to the fixed version the vendor names in its advisory. Fixed versions, as the CVE record's CNA (Echo Software Ltd.) states them: "Upgrade to ollama 0.17.1 or later."

Dependency Blast Radius

See which npm, PyPI, Go, and Maven packages are affected by CVE-2026-7482

Explore →

Is Your Infrastructure Affected by CVE-2026-7482?

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

Book a Demo →Browse All CVEs