LightLLM through 1.2.0 Missing Authentication on RL Control Routes
18Vexday Risk Score
No sign of exploitation. No public exploitation artifact known so far.
ssvc Trackcvss 8.7
exploitation probability
—
observed exploitation
nono source reports it
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.
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N
Affected products
ModelTC · LightLLMReferences
https://github.com/ModelTC/LightLLMhttps://github.com/ModelTC/lightllm/blob/v1.2.0/lightllm/server/api_http.py#L505-L507https://github.com/ModelTC/lightllm/blob/v1.2.0/lightllm/server/api_http_rl.py#L51-L139https://github.com/ModelTC/LightLLM/issues/1609https://www.vulncheck.com/advisories/lightllm-through-1.2.0-missing-authentication-on-rl-control-routes