Vulnerability Database

362,557

Total vulnerabilities in the database

CVE-2026-30762 — lightrag-hku

Improper Authentication

Summary: The file lightrag/api/config.py (line 397) uses a default JWT secret "lightrag-jwt-default-secret" when the TOKEN_SECRET environment variable is not set. The AuthHandler in lightrag/api/auth.py (lines 24-25) uses this secret to sign and verify tokens. An unauthenticated attacker can forge valid JWT tokens using the publicly known default secret and gain access to any protected endpoint.

Reproduction:

  1. Install LightRAG v1.4.10 with AUTH_ACCOUNTS configured but no TOKEN_SECRET set
  2. Use PyJWT to sign a token: jwt.encode({"sub": "admin", "role": "user"}, "lightrag-jwt-default-secret", algorithm="HS256")
  3. Send a request to any protected endpoint with the header: Authorization: Bearer <forged_token>
  4. Access is granted without valid credentials

Suggested Fix: Require TOKEN_SECRET to be explicitly set when AUTH_ACCOUNTS is configured. Refuse to start the API server if authentication is enabled but no custom secret is provided.


Venkata Avinash Taduturi [email protected]

CVSS v3:

  • Severity: High
  • Score: 7.5
  • AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N

Frequently Asked Questions

A security vulnerability is a weakness in software, hardware, or configuration that can be exploited to compromise confidentiality, integrity, or availability. Many vulnerabilities are tracked as CVEs (Common Vulnerabilities and Exposures), which provide a standardized identifier so teams can coordinate patching, mitigation, and risk assessment across tools and vendors.

CVSS (Common Vulnerability Scoring System) estimates technical severity, but it doesn't automatically equal business risk. Prioritize using context like internet exposure, affected asset criticality, known exploitation (proof-of-concept or in-the-wild), and whether compensating controls exist. A "Medium" CVSS on an exposed, production system can be more urgent than a "Critical" on an isolated, non-production host.

A vulnerability is the underlying weakness. An exploit is the method or code used to take advantage of it. A zero-day is a vulnerability that is unknown to the vendor or has no publicly available fix when attackers begin using it. In practice, risk increases sharply when exploitation becomes reliable or widespread.

Recurring findings usually come from incomplete Asset Discovery, inconsistent patch management, inherited images, and configuration drift. In modern environments, you also need to watch the software supply chain: dependencies, containers, build pipelines, and third-party services can reintroduce the same weakness even after you patch a single host. Unknown or unmanaged assets (often called Shadow IT) are a common reason the same issues resurface.

Use a simple, repeatable triage model: focus first on externally exposed assets, high-value systems (identity, VPN, email, production), vulnerabilities with known exploits, and issues that enable remote code execution or privilege escalation. Then enforce patch SLAs and track progress using consistent metrics so remediation is steady, not reactive.

SynScan combines attack surface monitoring and continuous security auditing to keep your inventory current, flag high-impact vulnerabilities early, and help you turn raw findings into a practical remediation plan.