CVE-2026-103243 LightLLM through 1.2.0 Server-Side Request Forgery via multimodal endpoints
Unauthenticated attackers can exploit LightLLM multimodal endpoints to perform server-side request forgery, accessing internal resources and network topology.
- Exploited in the wild
- Not known
- Login needed
- Not needed
- Attackable
- Over the internet
- Victim action needed
- Not needed
- Fix
- None listed
What is CVE-2026-103243?
CVE-2026-103243 is a medium-severity server-side request forgery vulnerability in ModelTC LightLLM, published on 30 Sep 2026. An attacker can exploit it over the internet without logging in, with no action from the victim.
Official description
LightLLM through 1.2.0 fails to validate image_url and audio_url parameters in multimodal endpoints, allowing unauthenticated attackers to perform server-side request forgery. Attackers can supply arbitrary URLs to fetch internal resources, with vision model processing disclosing content or error responses revealing internal network topology.
Weakness: CWE-918
Which versions are affected by CVE-2026-103243?
How do I fix CVE-2026-103243?
No fix has been published for CVE-2026-103243 yet. Limit exposure of the affected software until one is available.
Upgrade, and send outbound requests through an allow-list that blocks internal addresses. More about Server-side request forgery.
Is CVE-2026-103243 being exploited?
It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-103243 exists.
Sources
Also known as GHSA-26q6-mgpf-f836.