ClawHub
Back to skill

Security audit

腾讯会议冲突检查

Security checks across malware telemetry and agentic risk

Overview

This skill coherently checks Tencent Meeting conflicts and can run a disclosed scheduled watcher, with meeting-data access tied to that purpose.

Install only if you are comfortable letting the skill read your visible Tencent Meeting list through the tmeet CLI and store local conflict state containing meeting subjects, meeting numbers, times, and status. Use a private state directory for the watcher, and be aware that the Windows setup depends on external npm and Python packages.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Lp3

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding
The skill instructs the agent to read local reference files, execute shell commands (`tmeet`, `python3`, `py -3`), and use a watcher script, but it declares no permissions. That mismatch can cause the host or reviewer to underestimate the skill's capabilities, reducing oversight around command execution and file access.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.