Vulnerability 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.
CVSS Score
CRITICAL
Related Weaknesses (CWE)
References
- https://access.redhat.com/security/cve/CVE-2026-117574
- https://bugzilla.redhat.com/show_bug.cgi?id=2494861
FAQ
What is CVE-2026-117574?
CVE-2026-117574 is a vulnerability with a CVSS score of 9.1 (CRITICAL). 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 b...
How severe is CVE-2026-117574?
CVE-2026-117574 has been rated CRITICAL with a CVSS base score of 9.1/10. This is considered a critical vulnerability requiring immediate attention.
Is there a patch for CVE-2026-117574?
Check the references section above for vendor advisories and patch information. Review vendor security bulletins for remediation guidance.