high7.5
CVE-2026-103270
LightLLM through 1.2.0 mounts reinforcement learning control routes on the public HTTP API without authentication checks.
Impact
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.
Affected products
| Product | Affected versions |
|---|---|
| LightLLM | through 1.2.0 |
Versions were read from the advisory text. No structured product data has been published for this record yet.
Weakness classification
References
- NVD record
- CVE.org record
- https://github.com/ModelTC/LightLLM
- https://github.com/ModelTC/LightLLM/issues/1609
- https://github.com/ModelTC/lightllm/blob/v1.2.0/lightllm/server/api_http.py#L505-L507
- https://github.com/ModelTC/lightllm/blob/v1.2.0/lightllm/server/api_http_rl.py#L51-L139
- https://www.vulncheck.com/advisories/lightllm-through-1.2.0-missing-authentication-on-rl-control-routes
- https://github.com/ModelTC/LightLLM/issues/1609