ClawHub
Back to skill

Security audit

Microsoft To Do

Security checks across malware telemetry and agentic risk

Overview

This Microsoft To Do skill is a disclosed connector wrapper that can read and modify tasks, with clear confirmation requirements for changes and deletions.

Install this only if you trust OOMOL to mediate access to your Microsoft To Do account. Read-only list/get actions may run directly, but verify the exact task/list and payload before approving creates or updates, and approve deletions only when you are sure the target is correct.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The trigger text says to use this skill for ANY Microsoft To Do request and instead of calling the API directly, which is an overly broad routing rule. This can cause the agent to invoke a state-changing integration in situations where a narrower, task-scoped tool selection policy would be safer, increasing the chance of unnecessary data access or accidental writes/deletes in a user's Microsoft To Do account.

VirusTotal

57/57 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.