CVE Catalog

CVE-2026-117574

CriticalCVSS 9.1
Published: Updated: Translated: NVD NIST

Summary

In ai-gateway-payload-processing, an authenticated remote attacker can specify another tenant's model identifier in the request body or header. The service does not verify authorization before retrieving credentials from the shared store, so it injects the target tenant's API keys into the request.

Risk Assessment

An attacker can perform unauthorized requests and consume another tenant's LLM resources and quotas, breaking tenant isolation and causing cost impact.

Recommendation

Enforce tenant authorization checks before retrieving credentials from the shared store and update ai-gateway-payload-processing to a patched version.

Related vulnerabilities

Original NVD description (English source)

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.

Vulnerability data from NVD (NIST) · CISA KEV · EPSS