{"id":"CVE-2026-103270","published":"2026-09-30T15:22:26.903","lastModified":"2026-09-30T16:17:08.847","description":"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.","cvssScore":7.5,"cvssSeverity":"HIGH","cvssVector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H","cwes":["CWE-306"],"vendors":[],"products":[],"references":[{"url":"https://github.com/ModelTC/LightLLM","tags":[]},{"url":"https://github.com/ModelTC/LightLLM/issues/1609","tags":[]},{"url":"https://github.com/ModelTC/lightllm/blob/v1.2.0/lightllm/server/api_http.py#L505-L507","tags":[]},{"url":"https://github.com/ModelTC/lightllm/blob/v1.2.0/lightllm/server/api_http_rl.py#L51-L139","tags":[]},{"url":"https://www.vulncheck.com/advisories/lightllm-through-1.2.0-missing-authentication-on-rl-control-routes","tags":[]},{"url":"https://github.com/ModelTC/LightLLM/issues/1609","tags":[]}],"exploitRefs":[{"url":"https://github.com/ModelTC/LightLLM","tags":[]},{"url":"https://github.com/ModelTC/LightLLM/issues/1609","tags":[]},{"url":"https://github.com/ModelTC/lightllm/blob/v1.2.0/lightllm/server/api_http.py#L505-L507","tags":[]},{"url":"https://github.com/ModelTC/lightllm/blob/v1.2.0/lightllm/server/api_http_rl.py#L51-L139","tags":[]},{"url":"https://github.com/ModelTC/LightLLM/issues/1609","tags":[]}],"hasPoc":true,"ai":{"summary":"LightLLM 1.2.0 and earlier allows unauthenticated access to critical reinforcement learning control endpoints that can halt inference operations and wedge workers, enabling disruption of AI model serving without any authentication.","exploitability":"Easy to exploit with no preconditions; attackers only need to send HTTP requests to the exposed control endpoints like /pause_generation or /abort_request to disrupt services.","blast_radius":"Affects deployments using --enable_rl flag where attackers can halt inference operations, potentially causing service disruption and resource exhaustion across multiple workers in a LightLLM deployment.","remediation":"Upgrade to 1.2.1 or later to receive the fix for authentication checks on reinforcement learning control routes.","detection":"No reliable host or network indicator is derivable from the published description.","tags":["recon","denial-of-service","web"],"model":"garnet-coder","analyzedAt":"2026-10-17T09:04:31.858Z"}}