9.9

CVSS Score

3.1

-

CVSS Score

Basic Information

Concerned about an active attack path?

Talk to our security experts and see Miggo in action.

Miggo Vulnerability Database

→

CVE-2026-22688

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 stdio_config.command/args into MCP stdio settings, causing the server to execute subprocesses using these injected values. This issue has been patched in version 0.2.5.

(GitHub Advisory)

Miggo Vulnerability Database

→

CVE-2026-22688

CVE-2026-22688:

9.9

CVSS Score

3.1

-

CVSS Score

Basic Information

Is this CVE running in your environment?

Easily map the attack path and prioritize which CVEs are a threat to your organization

Validate Exposure

Technical Details

Package Name	Ecosystem	Vulnerable Versions	First Patched Version
github.com/Tencent/WeKnora	go	< 0.2.5	0.2.5

Technical Details

Vulnerability Intelligence
Miggo AI

Root Cause Analysis

The vulnerability is a command injection flaw within the MCP (Multi-modal Content Platform) service management feature. Authenticated users could create or update an MCP service, setting the transport_type to 'stdio' and providing a malicious command and arguments in the stdio_config object. The application failed to validate this user-provided configuration. The vulnerable functions (*mcpServiceService).CreateMCPService and (*mcpServiceService).UpdateMCPService would accept this malicious data and save it to the database. The command execution was triggered by making a POST request to the /api/v1/mcp-services/{id}/test endpoint. This action calls the mcp.NewMCPClient function, which, prior to the patch, would read the malicious command from the configuration and use it to start a subprocess, leading to remote code execution. The fix involves adding a robust validation function, secutils.ValidateStdioConfig, which is now called from CreateMCPService, UpdateMCPService, and NewMCPClient to ensure that only whitelisted commands and safe arguments are processed, effectively preventing the injection.

Vulnerable functions

Only Mi**o us*rs **n s** t*is s**tion

Vulnerability Intelligence
Miggo AI

Unlock WAF rules for this CVE

Generate vendor-ready rules for the observed attack patterns, plus reasoning and safe deployment guidance

Get WAF rules

WAF Protection Rules

WAF Rule

W** rul*s *v*il**l* *or Mi**o *ustom*rs only.W** rul*s *v*il**l* *or Mi**o *ustom*rs only.W** rul*s *v*il**l* *or Mi**o *ustom*rs only.W** rul*s *v*il**l* *or Mi**o *ustom*rs only.W** rul*s *v*il**l* *or Mi**o *ustom*rs only.W** rul*s *v*il**l* *or Mi**o *ustom*rs only.W** rul*s *v*il**l* *or Mi**o *ustom*rs only.W** rul*s *v*il**l* *or Mi**o *ustom*rs only.W** rul*s *v*il**l* *or Mi**o *ustom*rs only.W** rul*s *v*il**l* *or Mi**o *ustom*rs only.

Reasoning

*v*il**l* *or Mi**o *ustom*rs only.*v*il**l* *or Mi**o *ustom*rs only.*v*il**l* *or Mi**o *ustom*rs only.*v*il**l* *or Mi**o *ustom*rs only.*v*il**l* *or Mi**o *ustom*rs only.*v*il**l* *or Mi**o *ustom*rs only.*v*il**l* *or Mi**o *ustom*rs only.*v*il**l* *or Mi**o *ustom*rs only.*v*il**l* *or Mi**o *ustom*rs only.*v*il**l* *or Mi**o *ustom*rs only.