ClawHub
Back to skill

Security audit

Meeting Minutes CN

Security checks across malware telemetry and agentic risk

Overview

This skill clearly does what it advertises: creates meeting minutes, can sync them to Feishu, and can save action items for follow-up.

Install this only if you are comfortable with meeting notes being sent to Feishu and action items being retained locally. Review the separate feishu-doc skill before using sync, and ask the agent for a local markdown-only output when the meeting contains confidential material.

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
93% confidence
Finding
The skill instructs the agent to sync meeting minutes to Feishu and write action items to local memory, but it does not require explicit user consent or provide any warning that potentially sensitive meeting content will be persisted to external and internal storage. Meeting notes often contain confidential business discussions, attendee identities, and deadlines, so silent persistence increases the risk of unintended data disclosure or retention.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The template explicitly states that meeting minutes are automatically synced to Feishu, but it provides no notice, consent step, or data-handling guidance. Because meeting minutes often contain sensitive business discussions, attendee identities, decisions, and action items, automatic external transmission can create a privacy and confidentiality risk if users are unaware or if the workspace is misconfigured.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.