CVE-2026-103270
HIGHCVSS 7.5Description
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.
Timeline
Published:September 30th, 2026 3:22 PM
Last modified:September 30th, 2026 4:17 PM
CVSS Scoring
CVSS v3: 7.5 (HIGH)
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
Weaknesses (CWE)
References & Reports
Advisories, patches, and third-party reports
- 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
Source: NIST NVD · Data may lag official sources by up to one minute