10 results · Clear filters · Feed
-
Medium 5.3
WeKnora before 0.8.2 SSRF Guard Bypass via NAT64 IPv6 Addresses
WeKnora before 0.8.2 contains a server-side request forgery vulnerability in isRestrictedIP() that misclassifies NAT64-prefixed IPv6 addresses as public. Authenticated attackers can supply URLs resolving to NAT64 encodings of internal addresses via web_fetch …
-
Medium 6.3
Tencent WeKnora SQL Validator inject.go validateSubquery sql injection
A security vulnerability has been detected in Tencent WeKnora up to 0.8.1. Impacted is the function validateSubquery of the file internal/utils/inject.go of the component SQL Validator. The manipulation leads to sql injection. The attack is possible to be car…
-
Medium 6.5
WeKnora before 0.7.0 SSRF via Unvalidated HTTP Redirects
WeKnora before 0.7.0 fails to re-validate HTTP redirect targets in the POST /api/v1/knowledge-bases/:id/knowledge/url endpoint when downloading documents from user-supplied URLs. Authenticated attackers can bypass initial SSRF validation by supplying a public…
-
Medium 6.3
Tencent WeKnora Config API Endpoint initialization.go getKnowledgeBaseForInitialization authorization
A vulnerability has been found in Tencent WeKnora up to 0.3.6. Affected by this issue is the function getKnowledgeBaseForInitialization of the file internal/handler/initialization.go of the component Config API Endpoint. The manipulation of the argument kbId …
-
Medium 5.3
WeKnora: Broken Access Control - Cross-Tenant Data Exposure
WeKnora is an LLM-powered framework designed for deep document understanding and semantic retrieval. Prior to version 0.2.12, a broken access control vulnerability in the database query tool allows any authenticated tenant to read sensitive data belonging to …
-
Medium 6.5
WeKnora: DNS Rebinding Vulnerability in web_fetch Tool Allows SSRF to Internal Resources
WeKnora is an LLM-powered framework designed for deep document understanding and semantic retrieval. Prior to version 0.3.0, a DNS rebinding vulnerability in the web_fetch tool allows an unauthenticated attacker to bypass URL validation and access internal re…
-
Medium 5.3
WeKnora: Unauthorized Cross‑Tenant Knowledge Base Cloning
WeKnora is an LLM-powered framework designed for deep document understanding and semantic retrieval. Prior to version 0.3.0, a cross-tenant authorization bypass in the knowledge base copy endpoint allows any authenticated user to clone (duplicate) another ten…
-
Medium 5.9
WeKnora: Tool Execution Hijacking via Ambigous Naming Convention In MCP client and Indirect Prompt Injection
WeKnora is an LLM-powered framework designed for deep document understanding and semantic retrieval. Prior to version 0.3.0, a vulnerability involving tool name collision and indirect prompt injection allows a malicious remote MCP server to hijack tool execut…
-
Medium 5.9
WeKnora: SSRF via Redirection
WeKnora is an LLM-powered framework designed for deep document understanding and semantic retrieval. Prior to version 0.2.12, the application's "Import document via URL" feature is vulnerable to Server-Side Request Forgery (SSRF) through HTTP redirects. While…
-
Medium 5.6
WeKnora vulnerable to SQL Injection
WeKnora is an LLM-powered framework designed for deep document understanding and semantic retrieval. Prior to version 0.2.5, after WeKnora enables the Agent service, it allows users to call the database query tool. Due to insufficient backend validation, an a…