GHSA-67Q9-58VJ-32QX WeKnora Vulnerable to Tool Execution Hijacking via Ambigous Naming Convention In MCP client and Indirect Prompt Injection

Summary A vulnerability involving tool name collision and indirect prompt injection allows a malicious remote MCP server to hijack tool execution. By exploiting an ambiguous naming convention in the MCP client mcpservicetool, an attacker can register a malicious tool that overwrites a legitimate...

WeKnora Vulnerable to Broken Access Control in Tenant Management

Summary An authorization bypass in tenant management endpoints of WeKnora application allows any authenticated user to read, modify, or delete any tenant by ID. Since account registration is open to the public, this vulnerability allows any unauthenticated attacker to register an account and...

PT-2026-23799

Name of the Vulnerable Software and Affected Versions WeKnora versions prior to 0.3.0 Description WeKnora, an LLM-powered framework for deep document understanding and semantic retrieval, is susceptible to a vulnerability involving tool name collision and indirect prompt injection. A malicious...

Command Injection

github.com/tencent/weknora is vulnerable to command injection. The vulnerability is due to improper validation of user-supplied stdioconfig.command and args in MCP stdio settings, which allows an authenticated attacker to inject arbitrary commands and cause the server to execute malicious...

SUSE CVE-2026-22687

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 prompt-based bypass...

SUSE CVE-2026-22688

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 stdioconfig.command/args into MCP stdio settings, causing the server to execute...

CVE-2026-22687

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 prompt‑based bypass...

CVE-2026-22688

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 stdioconfig.command/args into MCP stdio settings, causing the server to execute...

GO-2026-4292 WeKnora has Command Injection in MCP stdio test in github.com/Tencent/WeKnora

WeKnora has Command Injection in MCP stdio test in github.com/Tencent/WeKnora...

GO-2026-4293 WeKnora vulnerable to SQL Injection in github.com/Tencent/WeKnora

WeKnora vulnerable to SQL Injection in github.com/Tencent/WeKnora...

Arbitrary Command Injection

Overview Affected versions of this package are vulnerable to Arbitrary Command Injection via the stdioconfig.command or stdioconfig.args parameters in MCP stdio settings. An attacker can execute arbitrary system commands by injecting malicious values into these parameters. Remediation Upgrade...

CVE-2026-22688

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 stdioconfig.command/args into MCP stdio settings, causing the server to execute...

CVE-2026-22687

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 prompt‑based bypass...

EUVD-2026-1879

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 stdioconfig.command/args into MCP stdio settings, causing the server to execute...

CVE-2026-22688

WeKnora is vulnerable to a command-injection in MCP stdio settings (stdio_config.command/args) that can cause the server to execute subprocesses when a user is authenticated. Affected: WeKnora prior to v0.2.5; patched in v0.2.5. The issue is triggered via MCP stdio configuration values and has be...

CVE-2026-22688 WeKnora has Command Injection in MCP stdio test

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 stdioconfig.command/args into MCP stdio settings, causing the server to execute...

CVE-2026-22688 WeKnora has Command Injection in MCP stdio test

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 stdioconfig.command/args into MCP stdio settings, causing the server to execute...

CVE-2026-22688 WeKnora has Command Injection in MCP stdio test

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 stdioconfig.command/args into MCP stdio settings, causing the server to execute...

CVE-2026-22687 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 attacker can use prompt‑based bypass...

CVE-2026-22687

WeKnora up to version 0.2.4 has a SQL Injection risk via the Agent service’s database_query tool due to insufficient backend validation, enabling prompt-based bypass to access sensitive server/database information. The vulnerability stems from backend checks that fail to constrain SQL inputs (e.g...