CVE-2026-103270

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.

Affected Software

Weaknesses

• CWE-306: Missing Authentication for Critical Function

ADP Enrichment

CISA ADP Vulnrichment

• SSVC:
• Exploitation: poc
  • Automatable: yes
  • Technical Impact: partial

Additional References

• https://github.com/ModelTC/LightLLM/issues/1609

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

• ←Previous
• Next→