Quick Google Calendar Command Line Interface

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:24 PM UTC
• Version:
  1.0.2

Overview

This is a transparent Google Calendar helper, but it can read and change calendar events through the user's local gcalcli OAuth access.

Install only if you are comfortable letting an agent use your configured gcalcli account to read calendars and create, delete, or edit events. Edit the skill to require confirmation for all destructive actions if your calendar contains sensitive or high-impact events, and revoke gcalcli OAuth access when you no longer use it.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (4)

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: The skill explicitly instructs the agent to perform non-interactive deletion immediately when a match is deemed unambiguous, using `gcalcli delete --iamaexpert`, and only verifies after the destructive action. If the agent misidentifies the target due to parsing, ambiguous semantics, recurrence handling, or calendar data quirks, an event can be removed without the user seeing a final confirmation or irreversible-risk warning first.

Missing User Warnings

Low

• Confidence: 83% confidence
• Finding: The create flow mandates an overlap scan across all non-ignored calendars, even when the user may only intend to work within one calendar. That broadens data access and can expose the existence, timing, or titles of events from other calendars to the agent workflow without an explicit privacy notice or opt-in.

Autonomous Decision Making

Medium

• Category: Excessive Agency

Content

### Safety guards in place

The skill does NOT blindly delete. All of these must hold before executing without confirmation:

1. **Explicit user request** — the user must have asked for the action in their message.
2. **Single unambiguous match** — exactly one event matches in a tight, bounded time window.

• Confidence: 92% confidence
• Finding: without confirmation

Autonomous Decision Making

Medium

• Category: Excessive Agency

Content

**This skill intentionally skips user confirmation for unambiguous destructive actions (delete/edit).** This is a deliberate UX decision, not an oversight. Here's why and how it's kept safe:

### Why skip confirmation?

This skill is designed for personal assistant use via messaging apps (Telegram, WhatsApp, etc.), where:

• Confidence: 96% confidence
• Finding: skip confirmation

VirusTotal

64/64 vendors flagged this skill as clean.