Tencent Meeting Mcp

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:38 PM UTC
• Version:
  1.0.0

Overview

This is a coherent Tencent Meeting integration, but it can access sensitive meeting content and should be used with care.

Install only if you trust the Tencent Meeting MCP endpoint and the mcporter setup path. Use a least-privilege Tencent Meeting token where possible, keep the token out of logs and shared shells, and confirm authorization before accessing participant lists, recordings, transcript exports, recording links, meeting passwords, or host keys.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (3)

Description-Behavior Mismatch

Medium

• Confidence: 85% confidence
• Finding: The documentation exposes an additional capability, exporting realtime transcription records, that is not declared in the user-facing description. Hidden or under-disclosed data-export functionality is risky because users may consent to meeting lookup features without realizing the skill can extract larger bodies of potentially sensitive meeting content.

Missing User Warnings

Medium

• Confidence: 88% confidence
• Finding: The skill provides access to highly sensitive collaboration data including recordings, transcripts, participant lists, invitees, and waiting-room records, yet it does not present a clear privacy warning or consent boundary. In a meeting context, these data types can contain confidential business discussions and personal information, so omission of privacy guidance increases the chance of inappropriate disclosure or over-collection.

Missing User Warnings

Low

• Confidence: 81% confidence
• Finding: The setup instructions tell users to place a personal token in an environment variable but do not warn that this credential is sensitive or should be protected from logs, screenshots, shell history, and accidental disclosure. While environment variables are common, omitting handling guidance can lead to avoidable credential exposure and unauthorized API access.

VirusTotal

66/66 vendors flagged this skill as clean.