CVE-2026-117574

Affects: large language model

CVSS: CRITICAL · 9.1v3.1
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:L/A:L
Published: 2026-10-28
Weakness: CWE-639
Source: nvd.nist.gov/vuln/detail/CVE-2026-117574

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.

References

How GTK Cyber trains on this

AI security training at GTK Cyber covers the LLM and ML-pipeline vulnerability classes that vulnerabilities like CVE-2026-117574 fall into. Our hands-on courses are taught by Charles Givre and other practitioners who break and defend production AI systems.

AI Red-Teaming course →·Browse MITRE ATLAS techniques

Related AI/LLM CVEs

AI security training, taught by people who do the work.

Hands-on courses on adversarial AI, prompt injection, and ML pipeline security.

Explore AI Red-Teaming