ClawHub
Back to skill

Security audit

Computer Usage Summary

Security checks across malware telemetry and agentic risk

Overview

This skill locally summarizes ActivityWatch computer-usage data and its sensitive access is disclosed, scoped, and aligned with that purpose.

Before installing, understand that this skill is meant to read local computer-activity records and can reveal sensitive work patterns and window-title context. Keep ActivityWatch local, review any saved CSV/TSV reports before sharing them, and only provide browser history, recent documents, terminal history, or Screen Time totals when you intentionally want those sources used.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding
Without declared permissions the skill's intent is opaque and cannot be validated.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding
This is a mismatch because the description explicitly promises privacy-preserving live-state and Screen Time fallbacks when ActivityWatch records are unavailable, but the code contains no fallback logic at all and simply reports ActivityWatch as unavailable. In addition, the code performs extra reporting/classification functions not mentioned in the description: it loads a local JSON rules file, classifies activity into project/client/category/billable fields, and generates client-timesheet/weekly-review/app-trend style outputs. The core ActivityWatch summarization portion does match the description, but the missing fallback behavior and the undeclared classification/timesheet capabilities make the description inaccurate.

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
title is `confirmed` only when it directly supports the described activity.
5. When the user needs project/client or billable reporting, offer an optional
   local JSON `--rules` file. Match only sanitized titles. Explain that the
   first matching rule wins and never create or upload rules without consent.
6. For spreadsheet output, run one table per command:
   - `--format markdown --table apps` for chat.
   - `--format tsv --table apps` to copy directly into spreadsheet software.
Confidence
75% confidence
Finding
without consent

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.