ClawHub
Back to skill

Security audit

ioffice-mcp

Security checks across malware telemetry and agentic risk

Overview

The skill is coherent for iOffice facility management, but it exposes broad tenant data and destructive business actions without clear confirmation or scoping safeguards.

Install only if you are authorized by your employer to automate iOffice/Eptura Workplace access. Use a least-privilege token if possible, keep credentials out of shared project files, and require explicit review before delete, approve, cancel, check-in/check-out, deliver, return, archive, or user-management actions.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill exposes numerous destructive and privacy-sensitive actions such as deleting buildings, users, spaces, reservations, and handling visitor, mail, and employee directory data, but it does not instruct the agent to require explicit user confirmation or warn about irreversible effects. In an agent setting, this increases the chance of accidental destructive actions, unauthorized changes, or over-broad disclosure of workplace and personal data through natural-language prompts.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.