CVE-2026-111160 LightLLM through 1.2.0 Unauthenticated DoS via pd_kv_trans_params Deserialization
Unauthenticated attackers can crash the LightLLM inference worker by sending malicious pickle data to the generate endpoint, causing a denial of service.
- 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-2026-111160?
CVE-2026-111160 is a high-severity unsafe deserialization vulnerability in ModelTC LightLLM, published on 15 Oct 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 contains a denial of service vulnerability that allows unauthenticated attackers to crash the inference worker by supplying the internal pd_kv_trans_params field to the /generate endpoint. Attackers can send a single request whose parameters cause pickle.loads to fail in InferSamplingParams, killing the inference thread while /health stays up and all later requests hang until restart.
Weakness: CWE-502
Which versions are affected by CVE-2026-111160?
How do I fix CVE-2026-111160?
No fix has been published for CVE-2026-111160 yet. Limit exposure of the affected software until one is available.
Upgrade, and only deserialise data from trusted sources or with an allow-list of types. More about Unsafe deserialization.
Is CVE-2026-111160 being exploited?
It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-111160 exists.
Sources
Also known as GHSA-mxm5-3g25-25c6.