Connect your agent
AdvisoriesCriticalCheck your lockfilePluginHow it worksPricing Connect your agent

Advisory record · GHSA-f4vv-55c2-5789

LightRAG is Vulnerable to Authentication Bypass: hardcoded DEFAULT_TOKEN_SECRET and public /auth-status defeat LIGHTRAG_API_KEY protection

CVSS 9.3 CriticalCriticalEPSS 0.0051 · 43rd percentile

Critical, because:

  • CVSS score 9.3: 9.0 or more.

How we decide what’s critical

Published by the GitHub Advisory Database at 20 Jul 2026, 21:46 UTC. agentprime has not analysed this yet, so whether it affects any app is not known.

PackageEcosystemAffectedFixed in
lightrag-hkuPyPI<1.5.41.5.4
Identifiers
GHSA-f4vv-55c2-5789 · CVE-2026-61740 · PYSEC-2026-3475
Weakness (CWE)
CWE-287 · CWE-798
Tags
Published
20 Jul 2026
Updated
23 Jul 2026

Machine-written summary

Summary written by Claude Haiku from the source advisory. Not reviewed by a person.

lightrag-hku versions below 1.5.4 are affected when LIGHTRAG_API_KEY is set without AUTH_ACCOUNTS. A remote unauthenticated attacker can obtain a guest token, either by forging one with a hardcoded default signing secret or from an unauthenticated endpoint, and skip the API key check to read, delete and upload documents and run queries. Upgrade to 1.5.4.

Written 5 Nov 2026.

Not analysed yet

We haven’t published our analysis of this Advisory yet. Once a person has reviewed it, this page will say what’s vulnerable, what has to be true for your app to be affected, and how to check.

Severity and exploitation

ScoreRatingCVSSVectorSource
9.3 Critical 4.0 CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:L/SC:N/SI:N/SA:N CNA (GitHub_M)
  • CISA KEV Not listed.
  • EPSS 0.0051, the 43rd percentile, on 11 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.

Timeline

  1. 31 Oct 2026, 14:41 UTC First seen by agentprime
  2. 31 Oct 2026, 14:41 UTC Confirmed by OSV

Sources

Facts on this page come from the GitHub Advisory Database (CC-BY 4.0), OSV and the other sources listed, as published. We don’t reproduce full advisory descriptions, which can contain exploit code.