Signal is active with 1 mentions in latest observed window
Recommended action window: Monitor and triage in normal cycle
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.
Priority
LOW
Exploitation
NONE
PoC
NONE
Patch
NONE
Momentum
STABLE
⚠️ CVE-2026-117574 (9.1) ⚠️ ai-gateway-payload-processing, a multi-tenant gateway for LLM requests, lets any logged-in user spend another tenant's LLM quota. No fixed version is available yet. https://t.co/pPcDO5zu6D
An authenticated attacker can inject another tenant's model ID into an AI gateway — and the gateway fetches the victim's API keys and burns LLM quota. CVE-2026-117574 (CVSS 9.1): an authorization check missing before credential retrieval. Check tenant context first, not after.