ClawHub
Back to skill

Security audit

Work Schedule Assistant

Security checks across malware telemetry and agentic risk

Overview

This skill stores work schedules and optional attachments locally and can set a daily reminder, with those behaviors disclosed and aligned with its purpose.

Before installing, confirm you are comfortable with a local schedule ledger under ~/.openclaw/workspace/work-schedule/ and with copied work attachments being retained there. Only run the reminder setup if you want a persistent daily cron reminder and understand the target chat/channel it will announce to.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Lp3

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding
The skill instructs the agent to read environment variables, read and write local files, invoke shell commands, and handle network URLs, but it does not declare corresponding permissions. This creates a trust and containment problem: users and the platform cannot accurately assess or constrain what the skill may do, and the broad filesystem path (`~/.openclaw/workspace/work-schedule/`) plus shell-based operations increase the blast radius if the skill is misused or implemented unsafely.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.