CVEFinder.io

CVE-2025-12805

⚠️ high
🔍 Scan for this CVE
Summary

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 Score
8.1
High
EPSS Score
0.0
Exploit Probability
Published Date
2026-03-26
First Seen: 2026-03-27
📊 Relative Risk Intelligence

This CVE is High Risk - more severe than 77.3% of all 338,292 vulnerabilities in our database.

#76,799
Top 25% most severe
Severity Percentile
🎯 CISA SSVC Assessment Updated: Mar 30, 2026
🔍 Exploitation Status
None
No known exploits
⚙️ Automatable
NO
Requires human interaction
💥 Technical Impact
Total
Complete system compromise possible
SSVC data provided by CISA
Last Modified 2026-04-30
Source NVD 🔗
CVSS Vector 3.1 CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:N
CWE IDs (Weakness Types)

📦 Affected Products 1

🔗 References 4

🔗 Related CVEs 6

CVE ID Severity CVSS EPSS Summary Published
CVE-2026-15154 🔶 medium 6.5 0.2 A flaw was found in `guardrails-detectors`, a component of Red Hat OpenShift AI. This vulnerability, known as Regular Ex... 2026-07-08
CVE-2023-54365 ⚠️ high 7.5 0.6 Traefik before 2.10.5 and 3.0.0-beta4 is affected by a denial-of-service vulnerability in HTTP/2 request handling inheri... 2026-06-23
CVE-2026-42271 ⚠️ high 8.8 80.2 LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. From version 1.74.2 to before vers... 2026-05-08
CVE-2026-1462 ⚠️ high 7.8 0.4 A vulnerability in the `TFSMLayer` class of the `keras` package, version 3.13.0, allows attacker-controlled TensorFlow S... 2026-04-13
CVE-2026-5483 ⚠️ high 8.5 0.5 A flaw was found in odh-dashboard in Red Hat Openshift AI. This vulnerability in the `odh-dashboard` component of Red Ha... 2026-04-10
CVE-2024-7557 ⚠️ high 8.8 0.3 A vulnerability was found in OpenShift AI that allows for authentication bypass and privilege escalation across models w... 2024-08-12
These CVEs affect the same products