CVE-2025-12805

HIGHNVD 8.18.1
EchelonGraph scoreMEDIUM confidence

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

Score 8.1 from GitHub Security Advisory (severity: HIGH) published 2026-03-27. NVD baseline CVSS 8.1; sources differ by 0.0.

Triggered by: GitHub Security Advisory CVSS
Sources: EPSS, GitHub Security Advisory, NVD CVSS v3
8.1EG
EchelonGraph verdictPlan a fixRemediate within your standard update timelines (the SSVC decision on this page).
  • High severity, but no confirmed exploitation yet
CISA-KEV: Not listedEPSS PROB: 0.4%CVSS: 8.1Exploit: None knownExposed services: Not assessed

A fix is available — apply it.

A flaw was found in Red Hat OpenShift AI (RHOAI) llama-stack-operator. This vulnerability allows unauthorized access to Llama Stack services deployed in other namespaces via direct network requests, because no NetworkPolicy restricts access to the llama-stack service endpoint. As a result, a user in one namespace can access another user’s Llama Stack instance and potentially view or manipulate sensitive data.

CVSS v3
8.1
EG Score
8.1HIGHmedium confidence
EG Risk
37
EG Risk 37/100

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)
Severity81% × 45%
The EG Score, 8.1 of 10.
Exploitation0.4% × 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 low or medium mission impact; Track* at high (mission-essential systems).
Exploitation none (CISA Vulnrichment) · Automatable no (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.
EPSS PROB
0.4%
EPSS %ILE
30th
KEV
Not listed

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

A fix is available. Apply it within your standard update timelines.

Exploitation none (CISA Vulnrichment) · Automatable no (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)14 days if the affected system is publicly exposed; Fix on system upgrade if it is not.

In CISA KEV no (CISA's KEV catalog) · Automatable no (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

March 26, 2026

Last Modified

June 17, 2026

Advisory Details (4)

Auto-updated Apr 30, 2026
Patch available. Sources: redhat.
Red Hat

2413101 – (CVE-2025-12805) CVE-2025-12805 llama-stack-k8s-operator: Llama Stack service exposed across namespaces due to missing NetworkPolicy

https://bugzilla.redhat.com/show_bug.cgi?id=2413101
Red HatMentions a patch (unverified)

cve-details

https://access.redhat.com/security/cve/CVE-2025-12805
Red HatMentions a patch (unverified)
https://access.redhat.com/errata/RHSA-2026:2695
Red HatMentions a patch (unverified)
https://access.redhat.com/errata/RHSA-2026:2106

Vendor Advisories for CVE-2025-12805(2)

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

Patch Availability(2)

Vendor / EcosystemFix (by version range) / PatchReleasedSource
redhatrhoai/odh-llama-stack-k8s-operator-rhel9:17707883152026-02-12redhat
redhatrhoai/odh-llama-stack-k8s-operator-rhel9:17702242792026-02-05redhat

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.

Weakness Classification(1)

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

Data Freshness Timeline

(refreshed 11× in last 7d / 27× 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 97 of 250 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. 3 repeat rows among the latest 100 are merged into the row they repeat. The 153 oldest rows on record are not shown and were not checked, so the counts can still include repeats.

  1. 2026-10-15 16:30 UTCEPSS rescoreEPSS 0.4% · 30th percentile
  2. 2026-10-14 16:31 UTCEPSS rescoreEPSS 0.4% · 30th percentile
  3. 2026-10-13 16:31 UTCEPSS rescoreEPSS 0.4% · 30th percentile
  4. 2026-10-12 17:25 UTCEG score recompute
  5. 2026-10-12 16:32 UTCEPSS rescoreEPSS 0.4% · 30th percentile
  6. 2026-10-11 20:55 UTCEG score recompute
  7. 2026-10-11 19:05 UTCEG score recompute
  8. 2026-10-11 15:46 UTCEG score recompute
  9. 2026-10-11 13:46 UTCEPSS rescoreEPSS 0.4% · 30th percentile
  10. 2026-10-10 19:58 UTCEPSS rescoreEPSS 0.4% · 30th percentile
  11. 2026-10-09 20:06 UTCEPSS rescoreEPSS 0.4% · 30th percentile
  12. 2026-10-08 17:08 UTCEPSS rescoreEPSS 0.4% · 30th percentile
  13. 2026-10-07 23:46 UTCEPSS rescoreEPSS 0.4% · 30th percentile
  14. 2026-10-06 15:16 UTCEPSS rescoreEPSS 0.4% · 30th percentile
  15. 2026-10-05 17:42 UTCEPSS rescoreEPSS 0.4% · 30th percentile
  16. 2026-10-04 23:21 UTCEPSS rescoreEPSS 0.4% · 29th percentile
  17. 2026-10-03 14:24 UTCEPSS rescoreEPSS 0.4% · 30th percentile
  18. 2026-10-01 19:48 UTCEPSS rescoreEPSS 0.4% · 29th percentile
  19. 2026-09-30 15:02 UTCEPSS rescoreEPSS 0.4% · 29th percentile
  20. 2026-09-28 13:50 UTCEPSS rescoreEPSS 0.4% · 29th percentile
  21. 2026-09-26 15:57 UTCEPSS rescoreEPSS 0.4% · 29th percentile
  22. 2026-09-24 14:02 UTCEPSS rescoreEPSS 0.4% · 29th percentile
  23. 2026-09-23 13:46 UTCEPSS rescoreEPSS 0.4% · 32nd percentile
  24. 2026-09-22 14:47 UTCEPSS rescoreEPSS 0.4% · 32nd percentile
  25. 2026-09-20 20:14 UTCEPSS rescoreEPSS 0.4% · 32nd percentile
Show 72 more
  1. 2026-09-18 19:27 UTCEPSS rescoreEPSS 0.4% · 32nd percentile
  2. 2026-09-16 14:06 UTCEPSS rescoreEPSS 0.4% · 31st percentile
  3. 2026-09-16 05:13 UTCEPSS rescoreEPSS 0.4% · 31st percentile
  4. 2026-09-15 03:08 UTCEPSS rescoreEPSS 0.4% · 31st percentile
  5. 2026-09-13 16:45 UTCEPSS rescoreEPSS 0.4% · 31st percentile
  6. 2026-09-12 14:59 UTCEPSS rescoreEPSS 0.4% · 31st percentile
  7. 2026-09-11 14:51 UTCEPSS rescoreEPSS 0.4% · 31st percentile
  8. 2026-09-11 09:35 UTCEPSS rescoreEPSS 0.4% · 31st percentile
  9. 2026-09-10 09:33 UTCEPSS rescoreEPSS 0.4% · 31st percentile
  10. 2026-09-08 21:59 UTCEPSS rescoreEPSS 0.4% · 31st percentile
  11. 2026-09-07 16:00 UTCEPSS rescoreEPSS 0.4% · 31st percentile
  12. 2026-09-06 13:46 UTCEPSS rescoreEPSS 0.4% · 31st percentile
  13. 2026-09-04 13:59 UTCEPSS rescoreEPSS 0.4% · 31st percentile
  14. 2026-09-04 05:05 UTCEPSS rescoreEPSS 0.4% · 31st percentile
  15. 2026-09-02 14:10 UTCEPSS rescoreEPSS 0.4% · 31st percentile
  16. 2026-09-01 13:52 UTCEPSS rescoreEPSS 0.4% · 31st percentile
  17. 2026-08-30 19:16 UTCEPSS rescoreEPSS 0.4% · 31st percentile
  18. 2026-08-30 01:21 UTCEPSS rescoreEPSS 0.4% · 31st percentile
  19. 2026-08-28 21:40 UTCEPSS rescoreEPSS 0.4% · 31st percentile
  20. 2026-08-27 14:24 UTCEPSS rescoreEPSS 0.4% · 31st percentile
  21. 2026-08-26 14:45 UTCEPSS rescoreEPSS 0.4% · 31st percentile
  22. 2026-08-25 13:47 UTCEPSS rescoreEPSS 0.4% · 31st percentile
  23. 2026-08-24 14:15 UTCEPSS rescoreEPSS 0.4% · 31st percentile
  24. 2026-08-23 00:18 UTCEPSS rescoreEPSS 0.4% · 31st percentile
  25. 2026-08-21 23:48 UTCEPSS rescoreEPSS 0.4% · 31st percentile
  26. 2026-08-20 22:54 UTCEPSS rescoreEPSS 0.4% · 31st percentile
  27. 2026-08-19 17:02 UTCEPSS rescoreEPSS 0.4% · 31st percentile
  28. 2026-08-18 13:47 UTCEPSS rescoreEPSS 0.4% · 31st percentile
  29. 2026-08-17 13:46 UTCEPSS rescoreEPSS 0.4% · 31st percentile
  30. 2026-08-16 14:55 UTCEPSS rescoreEPSS 0.4% · 31st percentile
  31. 2026-08-16 10:04 UTCEG score recompute
  32. 2026-08-16 10:04 UTCVendor advisory
  33. 2026-08-16 10:04 UTCGHSA enrichmentGHSA-cq3g-qvxc-ghr5 · GitHub severity HIGH · GitHub CVSS 8.1
  34. 2026-08-16 02:13 UTCEPSS rescoreEPSS 0.4% · 31st percentile
  35. 2026-08-15 01:29 UTCEPSS rescoreEPSS 0.4% · 31st percentile
  36. 2026-08-14 19:26 UTCVendor advisory
  37. 2026-08-14 19:26 UTCGHSA enrichmentGHSA-cq3g-qvxc-ghr5 · GitHub severity HIGH · GitHub CVSS 8.1
  38. 2026-08-14 06:23 UTCEG score recompute
  39. 2026-08-14 06:23 UTCVendor advisory
  40. 2026-08-14 06:23 UTCGHSA enrichmentGHSA-cq3g-qvxc-ghr5 · GitHub severity HIGH · GitHub CVSS 8.1
  41. 2026-08-13 21:59 UTCEPSS rescoreEPSS 0.4% · 31st percentile
  42. 2026-08-12 20:40 UTCEG score recompute
  43. 2026-08-12 20:40 UTCVendor advisory
  44. 2026-08-12 20:40 UTCGHSA enrichmentGHSA-cq3g-qvxc-ghr5 · GitHub severity HIGH · GitHub CVSS 8.1
  45. 2026-08-12 13:49 UTCEPSS rescoreEPSS 0.4% · 31st percentile
  46. 2026-08-11 20:48 UTCEG score recompute
  47. 2026-08-11 20:48 UTCVendor advisory
  48. 2026-08-11 20:48 UTCGHSA enrichmentGHSA-cq3g-qvxc-ghr5 · GitHub severity HIGH · GitHub CVSS 8.1
  49. 2026-08-11 13:41 UTCEPSS rescoreEPSS 0.4% · 31st percentile
  50. 2026-08-11 03:50 UTCEG score recompute
  51. 2026-08-11 03:50 UTCVendor advisory
  52. 2026-08-11 03:50 UTCGHSA enrichmentGHSA-cq3g-qvxc-ghr5 · GitHub severity HIGH · GitHub CVSS 8.1
  53. 2026-08-10 23:59 UTCEPSS rescoreEPSS 0.4% · 31st percentile
  54. 2026-08-10 06:20 UTCVendor advisory
  55. 2026-08-10 06:20 UTCGHSA enrichmentGHSA-cq3g-qvxc-ghr5 · GitHub severity HIGH · GitHub CVSS 8.1
  56. 2026-08-09 18:04 UTCEG score recompute
  57. 2026-08-09 18:04 UTCVendor advisory
  58. 2026-08-09 18:04 UTCGHSA enrichmentGHSA-cq3g-qvxc-ghr5 · GitHub severity HIGH · GitHub CVSS 8.1
  59. 2026-08-09 13:45 UTCEPSS rescoreEPSS 0.4% · 31st percentile
  60. 2026-08-09 05:56 UTCEG score recompute
  61. 2026-08-09 05:56 UTCVendor advisory
  62. 2026-08-09 05:56 UTCGHSA enrichmentGHSA-cq3g-qvxc-ghr5 · GitHub severity HIGH · GitHub CVSS 8.1
  63. 2026-08-08 04:30 UTCEG score recompute
  64. 2026-08-08 04:30 UTCVendor advisory
  65. 2026-08-08 04:30 UTCGHSA enrichmentGHSA-cq3g-qvxc-ghr5 · GitHub severity HIGH · GitHub CVSS 8.1
  66. 2026-08-07 16:26 UTCEPSS rescoreEPSS 0.4% · 31st percentile
  67. 2026-08-07 16:22 UTCVendor advisory
  68. 2026-08-07 16:22 UTCGHSA enrichmentGHSA-cq3g-qvxc-ghr5 · GitHub severity HIGH · GitHub CVSS 8.1
  69. 2026-08-06 18:45 UTCEG score recompute
  70. 2026-08-06 18:45 UTCVendor advisory
  71. 2026-08-06 18:45 UTCGHSA enrichmentGHSA-cq3g-qvxc-ghr5 · GitHub severity HIGH · GitHub CVSS 8.1
  72. 2026-08-06 13:45 UTCEPSS rescoreEPSS 0.4% · 31st percentile

Related CVEs(same vendor + same CWE)

Frequently asked(5)

What is CVE-2025-12805?
CVE-2025-12805 is a high-severity vulnerability; its CVE record was published on March 26, 2026. A flaw was found in Red Hat OpenShift AI (RHOAI) llama-stack-operator. This vulnerability allows unauthorized access to Llama Stack services deployed in other namespaces via direct network requests, because no NetworkPolicy restricts access to the llama-stack service endpoint. As a result, a user…
When was CVE-2025-12805 made public?
CVE-2025-12805 was made public on December 31, 2025: that is the date its CVE record's CNA, Red Hat, Inc., gives for when the vulnerability was made public. The CVE record itself was published on March 26, 2026. EchelonGraph's copy of the record carries a last-modified date of June 17, 2026; the record at its source may have been updated since.
Is CVE-2025-12805 actively exploited?
CVE-2025-12805 is not currently on CISA's Known Exploited Vulnerabilities catalog. FIRST EPSS estimates a 0.4% probability of exploitation in the next 30 days (30th percentile of EPSS-scored CVEs).
What is the CVSS score of CVE-2025-12805?
CVE-2025-12805 has a CVSS v3 base score of 8.1 (NVD).
How do I remediate CVE-2025-12805?
A fix for CVE-2025-12805 is available: update to the fixed version the vendor names in its advisory. The vendor advisories EchelonGraph has for CVE-2025-12805 are linked in the Vendor Advisories panel on this page.

Dependency Blast Radius

Explore the affected products and dependency analysis for CVE-2025-12805

Explore →

Is Your Infrastructure Affected by CVE-2025-12805?

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

Book a Demo →Browse All CVEs