Go modules package
github.com/tencent/weknora
pkg:golang/github.com/tencent/weknora
Vulnerabilities (10)
| CVE | Sev | CVSS | KEV | Affected versions | Fixed in | Published | Description |
|---|---|---|---|---|---|---|---|
| CVE-2026-30856 | Med | 5.9 | < 0.3.0 | 0.3.0 | Mar 7, 2026 | 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 execution. By exploiting a | |
| CVE-2026-30861 | — | >= 0.2.5, < 0.2.10 | 0.2.10 | Mar 7, 2026 | WeKnora is an LLM-powered framework designed for deep document understanding and semantic retrieval. From version 0.2.5 to before version 0.2.10, an unauthenticated remote code execution (RCE) vulnerability exists in the MCP stdio configuration validation. The application allows | ||
| CVE-2026-30860 | — | < 0.2.12 | 0.2.12 | Mar 7, 2026 | WeKnora is an LLM-powered framework designed for deep document understanding and semantic retrieval. Prior to version 0.2.12, a remote code execution (RCE) vulnerability exists in the application's database query functionality. The validation system fails to recursively inspect c | ||
| CVE-2026-30859 | — | < 0.2.12 | 0.2.12 | Mar 7, 2026 | 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 other tenants, includ | ||
| CVE-2026-30858 | — | < 0.3.0 | 0.3.0 | Mar 7, 2026 | 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 resources on the server | ||
| CVE-2026-30857 | — | < 0.3.0 | 0.3.0 | Mar 7, 2026 | 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 tenant’s knowledge base | ||
| CVE-2026-30855 | — | < 0.3.2 | 0.3.2 | Mar 7, 2026 | WeKnora is an LLM-powered framework designed for deep document understanding and semantic retrieval. Prior to version 0.3.2, an authorization bypass in tenant management endpoints of WeKnora application allows any authenticated user to read, modify, or delete any tenant by ID. Si | ||
| CVE-2026-30247 | — | < 0.2.12 | 0.2.12 | Mar 7, 2026 | 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 the backend implemen | ||
| CVE-2026-22688 | — | < 0.2.5 | 0.2.5 | Jan 10, 2026 | WeKnora is an LLM-powered framework designed for deep document understanding and semantic retrieval. Prior to version 0.2.5, there is a command injection vulnerability that allows authenticated users to inject stdio_config.command/args into MCP stdio settings, causing the server | ||
| CVE-2026-22687 | — | < 0.2.5 | 0.2.5 | Jan 10, 2026 | 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 attacker can use promp |
- affected < 0.3.0fixed 0.3.0
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 execution. By exploiting a
- CVE-2026-30861Mar 7, 2026affected >= 0.2.5, < 0.2.10fixed 0.2.10
WeKnora is an LLM-powered framework designed for deep document understanding and semantic retrieval. From version 0.2.5 to before version 0.2.10, an unauthenticated remote code execution (RCE) vulnerability exists in the MCP stdio configuration validation. The application allows
- CVE-2026-30860Mar 7, 2026affected < 0.2.12fixed 0.2.12
WeKnora is an LLM-powered framework designed for deep document understanding and semantic retrieval. Prior to version 0.2.12, a remote code execution (RCE) vulnerability exists in the application's database query functionality. The validation system fails to recursively inspect c
- CVE-2026-30859Mar 7, 2026affected < 0.2.12fixed 0.2.12
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 other tenants, includ
- CVE-2026-30858Mar 7, 2026affected < 0.3.0fixed 0.3.0
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 resources on the server
- CVE-2026-30857Mar 7, 2026affected < 0.3.0fixed 0.3.0
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 tenant’s knowledge base
- CVE-2026-30855Mar 7, 2026affected < 0.3.2fixed 0.3.2
WeKnora is an LLM-powered framework designed for deep document understanding and semantic retrieval. Prior to version 0.3.2, an authorization bypass in tenant management endpoints of WeKnora application allows any authenticated user to read, modify, or delete any tenant by ID. Si
- CVE-2026-30247Mar 7, 2026affected < 0.2.12fixed 0.2.12
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 the backend implemen
- CVE-2026-22688Jan 10, 2026affected < 0.2.5fixed 0.2.5
WeKnora is an LLM-powered framework designed for deep document understanding and semantic retrieval. Prior to version 0.2.5, there is a command injection vulnerability that allows authenticated users to inject stdio_config.command/args into MCP stdio settings, causing the server
- CVE-2026-22687Jan 10, 2026affected < 0.2.5fixed 0.2.5
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 attacker can use promp