Description (CNA)
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 (CNA)
| Vendor / product | Versions |
|---|---|
| ModelTC / LightLLM | affected 0 through 1.2.0 |
CWE
CWE-306
References
- 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://github.com/ModelTC/LightLLM
- https://www.vulncheck.com/advisories/lightllm-through-1.2.0-missing-authentication-on-rl-control-routes
ADP enrichment
No English description supplied.