ClawHub

Ai Meeting Helper

Security checks across malware telemetry and agentic risk

Overview

The skill appears to be a real meeting-transcription tool, but it uploads sensitive meeting content to OpenAI and has confusing credential and cleanup paths that users should review before installing.

Install only if you are comfortable sending meeting recordings, transcripts, and generated prompts to OpenAI. Use it on narrow folders, avoid sensitive or regulated meetings unless your policy allows this processing, prefer setting OPENAI_API_KEY explicitly in your shell, and manually check both the skill directory and its parent for .env and .ai_meeting_backup files when cleaning up.

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 (2)

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill processes meeting recordings and summaries via external OpenAI services, but the documentation does not warn that raw audio and transcript content leave the local environment. Meeting audio often contains confidential business information, personal data, and sensitive decisions, so users may unknowingly transmit regulated or proprietary content to a third party.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill sends audio content and derived meeting transcript data to an external API provider without any explicit consent flow, warning, or disclosure at the point of use. Because meetings commonly contain sensitive business, personal, or regulated information, silent transmission can create confidentiality, compliance, and privacy risks.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal