VDB

CVE-2025-12805

CVE-2025-12805 PUBLISHED CVSS 8.100000381469727 HIGH

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.

EPSS 0.02% · 4.0th percentile

Risk Scores

CVSS 3.1
8.100000381469727
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:N
EPSS Score
0.02%
4.0th percentile

Affected Products

VendorProductVersions
redhatopenshift_ai2.25
Red HatRed Hat OpenShift AI 2.25sha256:c0d95dfbae20e87113ffb81026d379bb63ad300447df98b27d1bf9a83b084744, sha256:1d258fe98c2477e4256a9b936f412f2501fb7ca9e3b810347f9712e0d5ce5c92, sha256:c0d95dfbae20e87113ffb81026d379bb63ad300447df98b27d1bf9a83b084744
Red HatRed Hat OpenShift AI (RHOAI)
Red HatRed Hat OpenShift AI (RHOAI)

Timeline

  • Mar 26, 2026 CVE Published
  • Mar 26, 2026 PoC Published
  • Mar 26, 2026 PoC Published
  • Mar 26, 2026 PoC Published
  • Mar 26, 2026 PoC Published
  • Mar 27, 2026 CVE Updated
  • Mar 27, 2026 Distribution Patch
  • Mar 27, 2026 Distribution Patch
  • Mar 27, 2026 Security Advisory
  • Mar 27, 2026 Security Advisory
  • Mar 27, 2026 PoC Published
  • Mar 29, 2026 Security Advisory
Open in Interactive Console →
$ Console Community · 100/wk Open console ›