ClawHub

Claw Calendar

Security checks across malware telemetry and agentic risk

Overview

This calendar skill is mostly transparent, but it gives an agent authority to change or delete calendar data without clear confirmation safeguards.

Install only if you trust the configured Claw Calendar server and can use a revocable API key. Before letting the agent change anything, require it to show the exact calendar and event details and ask for confirmation, especially for updates, deletes, and any calendar-level changes.

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 (3)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The trigger guidance is broad enough that the skill may activate for loosely related requests about schedules or reminders without clear user intent boundaries. In a skill that can create, update, and delete calendar data, overbroad activation increases the chance of unintended tool use and unauthorized modifications to a user's calendar.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The skill exposes update and delete operations on calendar events but does not instruct the agent to warn users, confirm destructive changes, or provide rollback-aware behavior. This creates a realistic risk of accidental loss or corruption of calendar data, especially if event selection or natural-language parsing is ambiguous.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill directs transmission of calendar content and an API key to a remote service without any privacy, data handling, or trust-boundary warning. Calendar entries often contain sensitive personal and business information, so sending titles, locations, descriptions, and timing data to an external API can expose private data if users are not clearly informed.

VirusTotal

51/51 vendors flagged this skill as clean.

View on VirusTotal