Back to skill

Security audit

Calendar Query

Security checks for vulnerabilities and agentic risk

Overview

This skill is a clear calendar-query helper, but it can read both work and personal calendars through an already-authenticated CLI with broad triggers and limited privacy guardrails.

Review before installing. This skill should only be used where Matt intentionally wants the agent to read these calendars. Prefer adding guardrails requiring explicit user permission before reading the personal calendar, limiting date ranges, and summarizing or redacting sensitive event details by default.

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
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Missing User Warnings

High
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill directs use of an already authenticated CLI to access both work and personal calendars, but provides no consent, minimization, or sensitivity handling guidance. This is dangerous because any agent invoking the skill can immediately retrieve sensitive scheduling data, including personal events, without explicit checks on necessity, audience, or least-privilege use.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The description uses very broad triggers like schedules, events, availability, or reminders, which can cause the skill to activate for many ordinary user requests without clearly limiting when sensitive calendar access is appropriate. In the context of an already authenticated calendar tool tied to both work and personal accounts, over-broad activation increases the chance of unnecessary exposure of private data.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.