Disclosure summary
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.
Source-reported weakness categories
CWE-306
Source-specific records & product guidance
Sources retain their own attribution and scoring. Follow the original record to confirm affected versions, fixed releases, and configuration conditions.
NIST National Vulnerability Database · NVD-CVE-2026-103270
Open original source · Updated Sep 30, 2026
Only CPE matches marked vulnerable=true are indexed. AND/OR platform conditions must be checked in the original NVD record.
Original records & references
- NIST NVD record
- CVE Program record
- github.com
- github.com
- github.com
- github.com
- www.vulncheck.com
- github.com
PUBLISHED 2026-09-30T11:22:26-04:00
MODIFIED 2026-09-30T12:17:08-04:00
INGESTED 2026-10-06T11:44:58-04:00