Yuque Mcp Tool

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent Yuque document-reading MCP setup, but users should treat the Yuque session cookie as a sensitive account credential.

Install only if you are comfortable giving the MCP client and connected AI agent access to the Yuque documents reachable by your session. Store the session value carefully, avoid sharing MCP config files, use the least-privileged Yuque account practical, and rotate or remove the session if the config may have been exposed.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill explicitly instructs users to retrieve a live `_yuque_session` cookie from browser developer tools and place it into MCP client configuration as an environment variable, but it does not clearly warn that this token is an authentication secret granting access to the user's Yuque content. In the context of an AI-connected MCP tool, exposing or mishandling this session can allow unauthorized document access, and users may not understand the credential sensitivity or persistence risks.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal