CVE-2026-46372

Affects: large language model

CVSS: HIGH · 8.5 v3.1
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:L/A:N
Published: 2026-05-29
Weakness: CWE-918
Source: nvd.nist.gov/vuln/detail/CVE-2026-46372

Description

SillyTavern is a locally installed user interface that allows users to interact with text generation large language models, image generation engines, and text-to-speech voice models. Prior to 1.18.0, SillyTavern exposes /api/search/searxng, which accepts attacker-controlled baseUrl and uses it directly to build outbound server-side fetches. An authenticated low-privilege user can point baseUrl at an internal or loopback HTTP service and receive the /search response body. This vulnerability is fixed in 1.18.0.

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-2026-46372 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