- Description
- 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.
- Source
- secalert@redhat.com
- NVD status
- Analyzed
- Products
- openshift_ai
CVSS 3.1
- Type
- Primary
- Base score
- 8.1
- Impact score
- 5.2
- Exploitability score
- 2.8
- Vector string
- CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:N
- Severity
- HIGH
- secalert@redhat.com
- CWE-653
- Hype score
- Not currently trending
CVE-2025-12805 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 namespa… https://t.co/dzXFv83jKD
@CVEnew
27 Mar 2026
184 Impressions
1 Retweet
1 Like
0 Bookmarks
0 Replies
0 Quotes
🟠 CVE-2025-12805 - 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 re... https://t.co/FRDBikPu1g https://t.co/2dG5giOmX9
@TheHackerWire
26 Mar 2026
117 Impressions
0 Retweets
0 Likes
0 Bookmarks
0 Replies
0 Quotes
[
{
"nodes": [
{
"cpeMatch": [
{
"criteria": "cpe:2.3:a:redhat:openshift_ai:2.25:*:*:*:*:*:*:*",
"matchCriteriaId": "F5696BAE-9A40-4A38-BC31-C51279913CE4",
"vulnerable": true
}
],
"negate": false,
"operator": "OR"
}
]
}
]