CVE-2026-103270

HIGHPre-NVD 7.57.5—
EchelonGraph scoreHIGH confidence

Score 7.5 from GitHub Security Advisory (severity: HIGH) published 2026-09-30. A secondary CVSS source baseline 7.5; sources differ by 0.0.

Triggered by: GitHub Security Advisory CVSS
Sources: epss, ghsa, secondary
Trending — 4 sources updated this weekElevated
7.5EG
EchelonGraph verdictPlan mitigationSerious severity, but no confirmed exploitation yet.
  • High severity, but no confirmed exploitation yet
CISA-KEV: Not listedEPSS PROB: 0.5%CVSS: 7.5Exploit: Elevated riskExposed services: Not assessed

No fix is confirmed yet — apply a workaround or compensating control (WAF / firewall / segmentation) and watch for the fix.

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.

CVSS v3
7.5
EG Score
7.5HIGHhigh confidence
EG Risk
65
EG Risk 65/100CISA SSVC

EG Risk is EchelonGraph's 0–100 priority score: it fuses intrinsic severity with real-world exploitation and automatability so you can rank equal-severity CVEs and fix the most dangerous first. Higher = act sooner. Distinct from the 0–10 EG Score (severity).

How it’s computed
Severity75% × 45%
Exploitation40% × 40%
Automatability100% × 15%
CISA SSVC: Track at low or medium mission impact; Attend at high (mission-essential systems).
Action: No fix is confirmed yet. Restrict network exposure of the affected system or apply the vendor's mitigation within your standard update timelines at low or medium mission impact and sooner than that at high, and watch the vendor's advisory for the fix.
EPSS PROB
0.5%
EPSS %ILE
41st
KEV
Not listed

CISA SSVCTrack at low or medium mission impact; Attend at high (mission-essential systems).

No fix is confirmed yet. Restrict network exposure of the affected system or apply the vendor's mitigation within your standard update timelines at low or medium mission impact and sooner than that at high, and watch the vendor's advisory for the fix.

Exploitation public PoC (CISA Vulnrichment) · Automatable yes (CISA Vulnrichment) · Technical impact partial (CISA Vulnrichment). Mission impact is CISA's Mission & Well-being decision point, and only you can judge it: high means the affected system is essential to your organisation's mission, or its compromise could cause irreversible harm to people. CISA's decision table

Published

September 30, 2026

Last Modified

September 30, 2026

Advisory Details (5)

Auto-updated Sep 30, 2026
No patch confirmed yet.
generic

LightLLM through 1.2.0 Missing Authentication on RL Control Routes | Advisories | VulnCheck

https://www.vulncheck.com/advisories/lightllm-through-1.2.0-missing-authentication-on-rl-control-routes
generic

GitHub - ModelTC/LightLLM: LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed performance. · GitHub

https://github.com/ModelTC/LightLLM
generic

LightLLM/lightllm/server/api_http_rl.py at v1.2.0 · ModelTC/LightLLM · GitHub

https://github.com/ModelTC/lightllm/blob/v1.2.0/lightllm/server/api_http_rl.py#L51-L139
generic

LightLLM/lightllm/server/api_http.py at v1.2.0 · ModelTC/LightLLM · GitHub

https://github.com/ModelTC/lightllm/blob/v1.2.0/lightllm/server/api_http.py#L505-L507
generic

[BUG] RL control routes are mounted unconditionally on the public API without authentication, allowing generation pause, targeted aborts, cache flush and worker wedging · Issue #1609 · ModelTC/LightLLM · GitHub

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

Vendor Advisories for CVE-2026-103270(1)

These vendors published their own advisory mentioning this CVE — often with vendor-specific remediation steps + affected product lists not in NVD.

Weakness Classification(1)

MITRE Common Weakness Enumeration — the root-cause categories this CVE belongs to.

Data Freshness Timeline

(refreshed 21× in last 7d / 21× in last 30d)

Each row is a source pipeline that fetched or updated this CVE on that date, with what changed. For example, "NVD update" means NVD published or revised its analysis for this CVE; "MITRE cvelistV5" means we ingested or refreshed it from the CNA feed. Most recent first.

  1. 2026-10-04 06:45 UTCGHSA enrichment
  2. 2026-10-03 18:26 UTCEG score recompute
  3. 2026-10-03 18:26 UTCGHSA enrichment
  4. 2026-10-03 14:25 UTCEPSS rescore
  5. 2026-10-03 06:04 UTCGHSA enrichment
  6. 2026-10-02 17:45 UTCEG score recompute
  7. 2026-10-02 17:45 UTCGHSA enrichment
  8. 2026-10-02 05:25 UTCEG score recompute
  9. 2026-10-02 05:25 UTCGHSA enrichment
  10. 2026-10-01 19:49 UTCEPSS rescore
  11. 2026-10-01 17:04 UTCGHSA enrichment
  12. 2026-10-01 04:45 UTCEG score recompute
  13. 2026-10-01 04:45 UTCGHSA enrichment
  14. 2026-09-30 16:22 UTCEG score recompute
  15. 2026-09-30 16:22 UTCGHSA enrichment
  16. 2026-09-30 16:12 UTCEG score recompute
  17. 2026-09-30 16:12 UTCGHSA enrichment
  18. 2026-09-30 15:37 UTCEG score recompute
  19. 2026-09-30 15:37 UTCGHSA enrichment
  20. 2026-09-30 14:52 UTCEG score recompute
  21. 2026-09-30 14:52 UTCMITRE cvelistV5first tracked

Related CVEs(same CWE)

Frequently asked(5)

What is CVE-2026-103270?
CVE-2026-103270 is a high vulnerability published on September 30, 2026. LightLLM through 1.2.0 mounts reinforcement learning control routes on the public HTTP API without authentication checks. Unauthenticated attackers can call endpoints like /pausegeneration, /abortrequest, /flushcache, and /initweightsupdategroup to disrupt inference operations and wedge workers on…
When was CVE-2026-103270 disclosed?
CVE-2026-103270 was first published on September 30, 2026. EchelonGraph re-ingests CVE updates from NVD on a 2-hour cycle, so this page reflects the latest published state.
Is CVE-2026-103270 actively exploited?
CVE-2026-103270 is not currently on CISA's Known Exploited Vulnerabilities catalog. FIRST EPSS estimates a 0.5% probability of exploitation in the next 30 days (41st percentile of EPSS-scored CVEs).
What is the CVSS score of CVE-2026-103270?
CVE-2026-103270 has a CVSS base score of 7.5 (a secondary CVSS source that NVD displays; NVD's own analysis pending).
How do I remediate CVE-2026-103270?
No fix for CVE-2026-103270 is confirmed yet. Until one is published, restrict network exposure of the affected system or apply the vendor's mitigation — for example, keep it off the internet or limit it to trusted networks — and watch the vendor's advisory for the fix. The vendor advisories EchelonGraph has for CVE-2026-103270 are linked in the Vendor Advisories panel on this page.

Dependency Blast Radius

Explore the affected products and dependency analysis for CVE-2026-103270

Explore →

Is Your Infrastructure Affected by CVE-2026-103270?

EchelonGraph automatically scans your cloud infrastructure and maps CVE exposure using blast radius analysis.

Book a Demo →Browse All CVEs