ClawHub
Back to skill

Security audit

Coordinate a Meeting

Security checks for vulnerabilities and agentic risk

Overview

This scheduling skill clearly uses meetlark.ai to create and manage meeting polls, with no hidden code or local persistence beyond an admin token the agent must keep private.

Before using it, assume meeting purpose, proposed time slots, and any participant names or emails you provide may be sent to meetlark.ai. Share only the minimum participant details needed, and keep the admin token private because it can be used to view results and close the poll.

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
  • 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
Confidence
95% confidence
Finding
The skill instructs the agent to create and distribute a poll through an external service and to collect participant information, but it does not warn the user that names, availability, and possibly email-related data will be sent to meetlark.ai. This creates a real privacy and consent risk because the agent may disclose third-party personal data to an external processor without explicit user awareness or confirmation.

Static analysis

No suspicious patterns detected.