ClawHub
Back to skill

Security audit

Meeting Analyzer

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed meeting-transcript analysis helper, with the main caution being that it processes private meeting content.

Install only if you are comfortable authorizing the Tencent Meeting or Feishu/Lark CLI tools and storing generated meeting reports locally. Meeting transcripts, participants, decisions, and action items may be sensitive, so confirm you have permission before processing or sharing the outputs.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Confidence
80% confidence
Finding
The invocation guidance uses broad natural-language triggers such as '分析这场会议' and '这个会议讲了什么' without clear boundaries or confirmation requirements. In an agentic environment, this can cause overbroad or unintended activation on ordinary conversation, leading the skill to fetch and process meeting links or transcripts that may contain sensitive corporate data.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.