Security audit

Calendar

Security checks for vulnerabilities and agentic risk

Overview

This calendar skill is coherent and purpose-aligned, with no executable code or hidden behavior, though users should understand it may involve calendar reads, event creation, and sync actions.

Install this only if you are comfortable letting an agent help with calendar data and potentially coordinate with Google, Apple, or Outlook calendars. Before event creation, edits, reminders, or sync, users should expect the agent to ask for confirmation even though the skill text does not explicitly require it.

A.I.G

Vulnerability Patterns

Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

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 (2)

Missing User Warnings

Medium

Confidence: 94% confidence
Finding: The skill description omits warnings that it may access sensitive calendar contents and perform provider synchronization with side effects across connected accounts. Users may not understand that invoking the skill could expose availability, meeting metadata, or propagate changes to external calendar providers, creating privacy and integrity risks.

Vague Triggers

Medium

Confidence: 92% confidence
Finding: The usage examples are broad, natural-language calendar requests that can match many ordinary user prompts without any clear activation boundary or confirmation requirement. In an agent ecosystem, this increases the chance of unintended skill invocation and accidental calendar actions such as reading schedules or creating events from ambiguous requests.

Static analysis

No suspicious patterns detected.