Security audit

Google Calendar (via gcalcli)

Security checks across malware telemetry and agentic risk

Overview

This skill transparently lets an agent manage Google Calendar through gcalcli, including event deletion, with clear limits and no hidden install or persistence behavior.

Install this only if you are comfortable letting an agent use your authenticated gcalcli setup to read and change Google Calendar events. Pay special attention to the documented choice to delete or edit a clearly matched event without a second confirmation; change that policy to always ask first if you want stricter control.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Missing User Warnings

Medium

Confidence: 94% confidence
Finding: The skill explicitly instructs non-interactive deletion using `gcalcli delete --iamaexpert` and also says to skip confirmation when a single match appears unambiguous. That creates a real risk of irreversible destructive actions from imperfect matching, calendar sync staleness, or model misunderstanding, especially because deletion is being optimized for speed rather than requiring an explicit user confirmation at execution time.

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

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.