Back to skill

Security audit

google-meet

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Google Meet integration that uses Maton OAuth/API tooling and includes appropriate user-approval guidance for writes, automation, credentials, and persistent forwarding.

Review the Google OAuth scopes and only authorize the account needed for the task. Treat writes, hosted functions, triggers, and any destination URL as separate approval points, especially because destinations can forward future event data automatically. Prefer Maton OAuth over long-lived API keys and avoid third-party forwarding unless you explicitly trust the host and understand what data will flow there.

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
  • 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