Back to skill

Security audit

Recipe Schedule Recurring Event

Security checks for vulnerabilities and agentic risk

Overview

This skill does what it says, but it can create a recurring Google Calendar event and invite an attendee without a clear confirmation step.

Before installing or running this skill, confirm that you want an agent to modify your primary Google Calendar and potentially send an invitation or notification to the listed attendee. Replace the sample event details and attendee with your intended values, and require confirmation before execution.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill instructs the agent to create a recurring Google Calendar event and include attendees, which causes persistent writes to the user's calendar and may immediately send invitations or notifications to third parties. Because the skill does not clearly warn about these side effects or require explicit user confirmation for the attendees, it can cause unintended scheduling changes, spam, disclosure of meeting details, and repeated external notifications.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.