CVE-2026-108943 ModelTC LightX2V Tokenizer cosmos3_runner.py AutoTokenizer.from_pretrained code injection
Local attackers can execute arbitrary code via the auto_map argument in the LightX2V tokenizer's AutoTokenizer.from_pretrained function.
- Exploited in the wild
- Not known
- Login needed
- Any signed-in user
- Attackable
- Local or same network only
- Victim action needed
- Not needed
- Fix
- None listed
What is CVE-2026-108943?
CVE-2026-108943 is a medium-severity code injection vulnerability in ModelTC LightX2V, published on 13 Oct 2026. It can only be exploited from the same machine or local network, with no action from the victim.
Official description
A weakness has been identified in ModelTC LightX2V up to 0.5.0. Affected is the function AutoTokenizer.from_pretrained of the file lightx2v/models/runners/cosmos3/cosmos3_runner.py of the component Tokenizer. This manipulation of the argument auto_map causes code injection. The attack is restricted to local execution. The exploit has been made available to the public and could be used for attacks. The project was informed of the problem early through an issue report but has not responded yet.
Which versions are affected by CVE-2026-108943?
How do I fix CVE-2026-108943?
No fix has been published for CVE-2026-108943 yet. Limit exposure of the affected software until one is available.
Upgrade, and never evaluate templates, expressions or code built from user input. More about Code injection.
Is CVE-2026-108943 being exploited?
It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-108943 exists.
Sources
Also known as GHSA-j5rm-qfch-8hjp.