CVE-2026-117574 Ai-gateway-payload-processing: ai-gateway-payload-processing: tenant/credential selection from client-controlled url path with no in-process authorization
CriticalCVSS 9.1
EPSS 0.24%
- Published
- Updated
- Exploit status
- No public exploit known
Description
A flaw was found in ai-gateway-payload-processing. An authenticated remote attacker can exploit this vulnerability by submitting a request specifying another tenant's model identifier in the request body or header. Because the service does not verify authorization before retrieving credentials from the shared store, it injects the target tenant's application programming interface (API) keys into the request. This flaw allows an attacker to perform unauthorized requests and consume another tenant's large language model (LLM) resources and quotas.
Affected products
| Product | Affected versions | Fixed in |
|---|---|---|
| redhat openshift ai | All versions | No fix listed |
| redhat/rhoai/odh-ai-gateway-payload-processing-rhel9(Red Hat:openshift_ai) | All versions | No fix listed |
References
- Red Hat CVE page vdb-entry vendor-advisory
- RHBZ#2494861 issue-tracking
- www.cve.org
- nvd.nist.gov