CVE-2026-103270
LightLLM through 1.2.0 mounts reinforcement learning control routes …
LightLLM through 1.2.0 mounts reinforcement learning control routes on the public HTTP API without authentication checks. Unauthenticated attackers can call endpoints like /pause_generation, /abort_request, /flush_cache, and /init_weights_update_group to disrupt inference operations and wedge workers on deployments started with --enable_rl.
What to do now
- Check your exposureFind out whether the affected software runs anywhere in your environment, including systems of suppliers.
- UpdateInstall the version in which the vendor fixed the vulnerability. The references lead to the advisory.
- Limit access until thenIf you cannot update at once, take the system off the internet or restrict who can reach it.
References
- github.com/ModelTC/LightLLM
- github.com/ModelTC/LightLLM/issues/1609
- github.com/ModelTC/lightllm/blob/v1.2.0/lightllm/server/api_http.py#L505-L507
- github.com/ModelTC/lightllm/blob/v1.2.0/lightllm/server/api_http_rl.py#L51-L139
- www.vulncheck.com/advisories/lightllm-through-1.2.0-missing-authentication-on-rl-control-r
- nvd.nist.gov/vuln/detail/CVE-2026-103270
- cve.org/CVERecord?id=CVE-2026-103270
Data: CVE list and the NVD. This product uses data from the NVD API but is not endorsed or certified by the NVD.