Back to skill

Security audit

Recipe Create Meet Space

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Google Workspace recipe that creates a Google Meet space and emails its join link, with the main caution being to verify the recipient and meeting access settings before sending.

Before installing or using this recipe, confirm the Gmail recipient list and decide whether an OPEN Google Meet space is appropriate for your organization; anyone who receives or obtains the link may be able to join depending on Google Workspace policy.

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

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

This markdown file describes an outbound email action that shares a newly created Google Meet join URL, but it does not include any warning or disclosure about sending meeting information to others. Under the markdown-file criteria for missing user warnings, behaviors affecting privacy or external data sharing should be called out to the user.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.