Summary
generated automatically from NVD dataIn ai-gateway-payload-processing, an authenticated remote attacker can name another tenant's model identifier in a request body or header. The service does not check authorization before pulling credentials from the shared store, so it injects the victim tenant's API keys into the attacker's request (CWE-639). This lets the attacker make unauthorized requests and consume the other tenant's LLM resources and quotas. The CVSS v3.1 score is 9.1 (CRITICAL).
NVD 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.
EPSS · FIRST.org
0.24%probability of exploitation in the next 30 days
Higher than 14% of scored CVEs
EPSS (Exploit Prediction Scoring System) estimates, from observed exploitation activity, how likely a CVE is to be exploited in the next 30 days. It complements CVSS, which measures severity, not likelihood. Score of 2026-10-29, recomputed daily by FIRST.org.
CVSS v3.1 Score
Information
- Published
- 28 oct. 2026
- Updated
- 28 oct. 2026
- Status
- Awaiting Analysis
- Source
- secalert@redhat.com
Weaknesses (CWE)
Similar CVEs
Other vulnerabilities of type CWE-639
Know which CVEs hit the versions you run.
Add the product and its version: cveo.tech lists the CVEs that affect it right away, then alerts you by email when a new one affects it — including before NVD has finished its analysis. Free, an account is all it takes.