Security audit

Recipe Plan Weekly Schedule

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple Google Calendar scheduling recipe that clearly performs one calendar write, though users should notice its hard-coded dates before running it.

Before installing or using this skill, confirm you are comfortable letting it read your Google Calendar and create an event. Edit the example dates and event details first, because the provided commands use fixed dates rather than dynamically selecting the current week.

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

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
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

Confidence: 96% confidence
Finding: The skill explicitly instructs the agent to create a Google Calendar event, but it does not clearly warn the user that executing the recipe will modify data in their calendar. In an agentic setting, this can lead to unexpected state changes, accidental scheduling conflicts, or unauthorized-looking actions if the user did not intend to permit writes.

Static analysis

No suspicious patterns detected.