LightLLM through 1.2.0 Missing Authentication on RL Control Routes (CVE-2026-103270) | HOL Guard CVE

High · CVSS 8.7CVE-2026-103270

LightLLM through 1.2.0 Missing Authentication on RL Control Routes

Answer in brief

CVE-2026-103270 records a High severity (CVSS 8.7) vulnerability in LightLLM through 1.2.0 Missing Authentication on RL Control Routes. The current sources do not mark it as known exploited. The current feed maps ModelTC/LightLLM (generic). Check affected ranges and fixed versions before updating.

Analysis pending evidence review

HOL Guard separates source facts from reviewed analysis. See the methodology.

Published Sep 30, 2026Updated Sep 30, 2026Source checked Sep 30, 2026First seen by HOL Sep 30, 2026Material review Sep 30, 2026

Upstream Advisory

Key facts

Risk: High · CVSS 8.7
Exploitation: Not marked as known exploited
Affected software: 1 mapped package or product
Fix availability: Not reported

Why this deserves its current priority

CVSS is 8.7. The current sources do not mark it as known exploited. Treat this as a source-backed prioritization signal, not a statement about your environment.

Analysis status

Analysis pending evidence review

Factual feed record only; HOL analysis is not approved for indexing. Read the methodology.

Affected scope and exposure questions

The current feed maps ModelTC/LightLLM (generic). Check affected ranges and fixed versions before updating.

Mapped affected packages and fixed versions
Package	Affected range	Fixed version
ModelTC/LightLLMgeneric	>=0 <=1.2.0	Not reported

Recommended response

Check inventory. Check lockfiles and deployed manifests for ModelTC/LightLLM.
Review the reported fix. Monitor this advisory for an available fix and review any installs of the affected package.

Evidence timeline and material changes

Published upstream
Sep 30, 2026
Evidence: source:cvelist:source_dates:source-dates:record
Source modified
Sep 30, 2026
Evidence: source:cvelist:source_dates:source-dates:record
First seen by HOL
Sep 30, 2026

Sources and claim methodology

Upstream source description

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.

Quoted source text, attributed separately from HOL analysis.