WhenToMeet

• Outcome: Pass
• Latest audit: May 28, 2026 at 12:12 PM UTC
• Version:
  1.0.2

Overview

This is a documentation-only WhenToMeet API skill whose sensitive scheduling and calendar capabilities are disclosed and fit the stated scheduling purpose.

Install this only if you want an agent to use a WhenToMeet API key. Treat participant availability, booking details, and connected calendar accounts as private data, and require explicit confirmation before deleting events, canceling bookings, or showing account/calendar metadata.

SkillSpector

By NVIDIA

Vulnerability Patterns

• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• 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)

Description-Behavior Mismatch

Medium

• Confidence: 95% confidence
• Finding: The skill is advertised as group scheduling, but it documents additional capabilities for bookings, calendar connections, and analytics that expand access to potentially sensitive account and usage data. This mismatch can cause an agent or user to grant broader authority than expected, increasing the chance of privacy-impacting actions outside the stated purpose.

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: The skill documents a DELETE endpoint with no caution about destructive effects, confirmation requirements, or ownership checks at the prompt layer. In agentic use, this increases the risk of accidental or unauthorized deletion of scheduling data due to ambiguous user intent or unsafe automation.

Missing User Warnings

Medium

• Confidence: 94% confidence
• Finding: Listing connected calendar accounts exposes integration metadata that may reveal a user's linked providers and account configuration. Without a privacy warning or least-privilege guidance, an agent may retrieve and surface this sensitive information unnecessarily.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The event details example includes participant availability responses and display names, which are personal scheduling data. Presenting this without a privacy warning normalizes exposing attendee information and may lead agents to retrieve or disclose participant data more broadly than users expect.

VirusTotal

66/66 vendors flagged this skill as clean.