ClawHub
Back to skill

Security audit

Action Items

Security checks across malware telemetry and agentic risk

Overview

This skill is a meeting action-item organizer with coherent, disclosed behavior, though users should be careful before saving meeting follow-up history.

Install only if you are comfortable pasting meeting notes into the agent. Before saving follow-up history, confirm what will be retained, avoid storing raw sensitive transcripts when a short action-item summary is enough, and ask the agent not to save confidential meetings.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The trigger list includes very broad, common phrases such as asking what is pending from a meeting or organizing tasks, which can cause the skill to activate in situations where the user did not explicitly intend to invoke it. In this skill’s context, unintended activation could lead to parsing and optionally storing sensitive meeting content, increasing privacy and workflow risks even without malicious intent.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill proposes maintaining follow-up history in memory for future meetings, but it does not provide a clear upfront warning that meeting notes, owners, deadlines, and status data may persist beyond the current session. Because meeting content often contains sensitive business or personal information, silent or poorly disclosed persistence creates a real confidentiality and consent risk.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.