Ollama before 0.1.34 does not validate the format of the digest (sha256 with 64 hex digits) when getting the model path, and thus mishandles the TestGetBlobsPath test cases such as fewer than 64 hex digits, more than 64 hex digits, or an initial ../ substring.
CVE-2024-37032
“▲” beside the score: it is higher than NVD's CVSS score.
Score elevated to 9.0 because EPSS predicted 90% probability of exploitation within the next 30 days (99th percentile of EPSS-scored CVEs) when EchelonGraph scored this CVE. NVD baseline CVSS 8.8 retained for reference. Confidence: see factors.
Also known asEUVD-2024-1525 (ENISA EUVD) · GHSA-8hqg-whrw-pv92 (GitHub Security Advisories)Source: ENISA EUVD
- High exploitation likelihood — EPSS 90%
- Public exploit code is available (Metasploit, other public proof-of-concept code)
A fix is available — apply it.
- CVSS v3
- 8.8
- EG Score
- 9.0CRITICALhigh confidence
- EG Risk
- 75EG Risk 75/100
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)Severity88% × 45%Impact severity (EG Severity): CVSS 8.8 of 10. Never the KEV-floored or EPSS-lifted EG Score.Exploitation90% × 40%FIRST EPSS: the 30-day exploitation probability when EchelonGraph scored this CVE.Automatability0% × 15%CISA's SSVC Automatable value: no (Vulnrichment).SSVC (CISA's decision table, applied by EchelonGraph): Track at every mission impact level.Exploitation none (CISA Vulnrichment) · Automatable no (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 available. Apply it within your standard update timelines. - EPSS PROB
- 90%
- EPSS %ILE
- 99th
- 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 (9.0): severity, escalated by confirmed exploitation. This CVE's 9.0 is EPSS's lift toward 9.0 from its impact severity (EG Severity, CVSS 8.8 HIGH): a likelihood of exploitation, not impact.
- EG Severity
- 8.8 HIGHCVSS-B, impact only: no KEV listing, EPSS or EG-KEV tier raises it.NVD CVSS v3 · CVSS v3.0 or v3.1
- EG Likelihood
- 90% within 30 daysSource: FIRST EPSS (model v2026.06.15, score date 2026-11-01). 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 every mission impact level.CISA BOD 26-04: 60 days if the affected system is publicly exposed; Fix on system upgrade if it is not.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 every mission impact level.
A fix is available. Apply it within your standard update timelines.
Exploitation none (CISA Vulnrichment) · Automatable no (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)60 days if the affected system is publicly exposed; Fix on system upgrade if it is not.
The score's inputs: In CISA KEV no (CISA's KEV catalog) · Automatable no (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
May 31, 2024
Last Modified
May 1, 2025
Advisory Details (4)
Auto-updated Aug 24, 2026Probllama in Ollama: A tale of a yet another RCE vulnerability (CVE-2024-37032) - vsociety
https://www.vicarius.io/vsociety/posts/probllama-in-ollama-a-tale-of-a-yet-another-rce-vulnerability-cve-2024-37032validate the format of the digest when getting the model path
Fix merged in ollama/ollama PR #4175 on 2024-05-05 — awaiting tagged release
https://github.com/ollama/ollama/pull/4175Comparing v0.1.33...v0.1.34 · ollama/ollama · GitHub
https://github.com/ollama/ollama/compare/v0.1.33...v0.1.34ollama/server/modelpath_test.go at adeb40eaf29039b8964425f69a9315f9f1694ba8 · ollama/ollama · GitHub
https://github.com/ollama/ollama/blob/adeb40eaf29039b8964425f69a9315f9f1694ba8/server/modelpath_test.go#L41-L58Patch Availability(1)
| Vendor / Ecosystem | Fix (by version range) / Patch | Released | Source |
|---|---|---|---|
| go | github.com/ollama/ollama @ 0.1.34 (fixes < 0.1.34) | — | ghsa |
Patches are aggregated from vendor advisories (Red Hat, Microsoft, Cisco, GitHub) and package ecosystems (OSV, GHSA). Multiple rows for the same upstream release have been deduplicated.
Affected Packages
(1 across 1 ecosystem)
Go(1)
| Package | Vulnerable range | Fix by version range | Dependents |
|---|---|---|---|
| github.com/ollama/ollama | — |
| — |
Weakness Classification(1)
MITRE Common Weakness Enumeration — the root-cause categories this CVE belongs to.
Data Freshness Timeline
(refreshed 11× in last 7d / 37× 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 87 of 96 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. 13 repeat rows among the latest 100 are merged into the row they repeat. The 9 oldest rows on record are not shown and were not checked, so the counts can still include repeats.
- 2026-11-01 21:09 UTCEG score recompute
- 2026-11-01 21:09 UTCGHSA enrichmentGHSA-8hqg-whrw-pv92 · GitHub severity MODERATE
- 2026-11-01 08:13 UTCGHSA enrichmentGHSA-8hqg-whrw-pv92 · GitHub severity MODERATE
- 2026-10-31 22:52 UTCEG score recompute
- 2026-10-31 00:35 UTCEG score recompute
- 2026-10-30 16:32 UTCEPSS rescoreEPSS 90% · 99th percentile
- 2026-10-30 02:18 UTCEG score recompute
- 2026-10-29 04:01 UTCEG score recompute
- 2026-10-28 16:29 UTCEPSS rescoreEPSS 90% · 99th percentile
- 2026-10-28 05:44 UTCEG score recompute
- 2026-10-27 07:28 UTCEG score recompute
- 2026-10-25 17:08 UTCEG score recompute
- 2026-10-25 16:30 UTCEPSS rescoreEPSS 90% · 99th percentile
- 2026-10-25 08:06 UTCEG score recompute
- 2026-10-24 09:48 UTCEG score recompute
- 2026-10-23 16:29 UTCEPSS rescoreEPSS 90% · 99th percentile
- 2026-10-23 11:30 UTCEG score recompute
- 2026-10-22 13:10 UTCEG score recompute
- 2026-10-21 16:29 UTCEPSS rescoreEPSS 90% · 99th percentile
- 2026-10-21 14:52 UTCEG score recompute
- 2026-10-19 17:15 UTCEG score recompute
- 2026-10-19 16:29 UTCEPSS rescoreEPSS 90% · 99th percentile
- 2026-10-18 18:58 UTCEG score recompute
- 2026-10-18 16:30 UTCEPSS rescoreEPSS 90% · 99th percentile
- 2026-10-18 07:12 UTCEG score recompute
Show 62 moreShow fewer
- 2026-10-17 20:40 UTCEG score recompute
- 2026-10-16 22:20 UTCEG score recompute
- 2026-10-15 18:59 UTCEG score recompute
- 2026-10-14 16:30 UTCEPSS rescoreEPSS 90% · 99th percentile
- 2026-10-14 12:44 UTCEG score recompute
- 2026-10-12 17:51 UTCEG score recompute
- 2026-10-12 14:09 UTCEG score recompute
- 2026-10-11 21:16 UTCEG score recompute
- 2026-10-11 16:09 UTCEG score recompute
- 2026-10-10 20:33 UTCOSV refresh
- 2026-10-07 23:46 UTCEPSS rescoreEPSS 90% · 99th percentile
- 2026-10-05 17:41 UTCEPSS rescoreEPSS 90% · 99th percentile
- 2026-09-30 19:47 UTCEG score recompute
- 2026-09-30 15:01 UTCEPSS rescoreEPSS 90% · 99th percentile
- 2026-09-29 15:17 UTCEPSS rescoreEPSS 90% · 99th percentile
- 2026-09-28 13:49 UTCEPSS rescoreEPSS 90% · 99th percentile
- 2026-09-24 14:01 UTCEPSS rescoreEPSS 90% · 99th percentile
- 2026-09-22 14:46 UTCEPSS rescoreEPSS 90% · 99th percentile
- 2026-09-21 20:32 UTCEPSS rescoreEPSS 90% · 99th percentile
- 2026-09-21 08:19 UTCOSV refresh
- 2026-09-20 20:14 UTCEPSS rescoreEPSS 90% · 99th percentile
- 2026-09-19 15:40 UTCEPSS rescoreEPSS 90% · 99th percentile
- 2026-09-16 14:06 UTCEPSS rescoreEPSS 90% · 99th percentile
- 2026-09-12 14:59 UTCEPSS rescoreEPSS 90% · 99th percentile
- 2026-09-08 21:58 UTCEPSS rescoreEPSS 90% · 99th percentile
- 2026-09-06 13:46 UTCEPSS rescoreEPSS 90% · 99th percentile
- 2026-09-05 15:26 UTCEPSS rescoreEPSS 90% · 99th percentile
- 2026-09-02 05:44 UTCOSV refresh
- 2026-08-30 19:15 UTCEPSS rescoreEPSS 90% · 99th percentile
- 2026-08-30 01:20 UTCEPSS rescoreEPSS 90% · 99th percentile
- 2026-08-28 21:39 UTCEPSS rescoreEPSS 90% · 99th percentile
- 2026-08-25 13:47 UTCEPSS rescoreEPSS 90% · 99th percentile
- 2026-08-24 14:15 UTCEPSS rescoreEPSS 90% · 99th percentile
- 2026-08-21 23:47 UTCEPSS rescoreEPSS 90% · 99th percentile
- 2026-08-16 06:59 UTCOSV refresh
- 2026-08-12 13:49 UTCEPSS rescoreEPSS 90% · 99th percentile
- 2026-08-10 23:58 UTCEPSS rescoreEPSS 90% · 99th percentile
- 2026-08-08 16:35 UTCEPSS rescoreEPSS 90% · 99th percentile
- 2026-08-05 19:16 UTCEPSS rescoreEPSS 90% · 99th percentile
- 2026-08-01 00:42 UTCOSV refresh
- 2026-07-30 16:26 UTCEPSS rescoreEPSS 90% · 99th percentile
- 2026-07-27 14:11 UTCEPSS rescoreEPSS 90% · 99th percentile
- 2026-07-24 14:16 UTCEPSS rescoreEPSS 90% · 99th percentile
- 2026-07-23 02:38 UTCEG score recompute
- 2026-07-22 14:07 UTCEPSS rescoreEPSS 90% · 99th percentile
- 2026-07-15 16:56 UTCEPSS rescoreEPSS 90% · 99th percentile
- 2026-07-15 01:59 UTCEPSS rescoreEPSS 90% · 99th percentile
- 2026-07-14 07:40 UTCOSV refresh
- 2026-07-08 15:13 UTCEPSS rescoreEPSS 90% · 99th percentile
- 2026-07-01 15:05 UTCEPSS rescoreEPSS 90% · 99th percentile
- 2026-06-27 03:07 UTCEPSS rescoreEPSS 90% · 99th percentile
- 2026-06-26 05:16 UTCOSV refresh
- 2026-06-24 14:04 UTCEPSS rescoreEPSS 90% · 99th percentile
- 2026-06-23 21:32 UTCEPSS rescoreEPSS 90% · 99th percentile
- 2026-06-22 14:25 UTCEPSS rescoreEPSS 90% · 99th percentile
- 2026-06-16 17:52 UTCEPSS rescoreEPSS 89% · 99th percentile
- 2026-06-15 17:47 UTCEPSS rescoreEPSS 89% · 99th percentile
- 2026-06-12 23:11 UTCEPSS rescoreEPSS 94% · 99th percentile
- 2026-06-10 13:21 UTCEPSS rescoreEPSS 94% · 99th percentile
- 2026-06-08 16:11 UTCOSV refresh
- 2026-06-08 14:16 UTCEPSS rescoreEPSS 94% · 99th percentile
- 2026-06-05 06:09 UTCEPSS rescoreEPSS 94% · 99th percentile
Publicly available exploits
(5 references)Public exploit code is referenced for this CVE (1 Metasploit module, 3 GitHub PoCs), as is 1 Nuclei detection template. A detection template checks whether a system is affected; it is not necessarily exploit code. Defenders should treat patch urgency accordingly.
- Metasploitexploit/linux/http/ollama_rce_cve_2024_37032✓ verifiedPublished Feb 25, 2026
Ollama Model Registry Path Traversal RCE
Open source ↗ - GitHub PoCitzSh4dowxZ/CVE-2024-37032-PoCPublished May 19, 2026
PoC for CVE-2024-37032 (Probllama): Ollama <=0.1.33 path traversal/arbitrary file write via model digest handling, using a FastAPI rogue registry, connector workflow, and shared object preload demo for authorized lab testing.
Open source ↗ - GitHub PoCpankass/CVE-2024-37032_CVE-2024-45436Published Oct 21, 2024
CVE-2024-45436
Open source ↗ - Nucleihttp/cves/2024/CVE-2024-37032.yamlPublished Jul 9, 2024
Ollama - Remote Code Execution
Open source ↗ - GitHub PoCBi0x/CVE-2024-37032Published Jun 26, 2024
Path traversal in Ollama with rogue registry server
Open source ↗
Related CVEs(same product + same CWE)
Same product
10 shownGo:github.com/ollama/ollama
Frequently asked(5)
What is CVE-2024-37032?
When was the CVE record for CVE-2024-37032 published?
Is CVE-2024-37032 actively exploited?
What is the CVSS score of CVE-2024-37032?
How do I remediate CVE-2024-37032?
Dependency Blast Radius
See which npm, PyPI, Go, and Maven packages are affected by CVE-2024-37032
Is Your Infrastructure Affected by CVE-2024-37032?
EchelonGraph automatically scans your cloud infrastructure and maps CVE exposure using blast radius analysis.