ClawHub
Back to skill

Security audit

Persona Event Coordinator

Security checks for vulnerabilities and agentic risk

Overview

The skill is a disclosed event-planning persona for Google Workspace actions, with no hidden code or persistence, though users should confirm recipient-facing sends and posts.

Install only if you want an agent to help operate across Google Workspace for event logistics. Before allowing it to send emails, create attendee-facing calendar events, upload shared materials, or post Chat announcements, review the recipients, spaces, links, and content to avoid accidental disclosure or premature messaging.

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
94% confidence
Finding
The skill directly instructs the agent to send emails, create calendar events with attendee lists, and announce updates in chat without requiring explicit user confirmation or warning that these are outbound actions involving third-party data disclosure. In an agent setting, this can cause unintended messages, privacy leaks, or premature sharing of event details and attendee information if the agent acts on ambiguous prompts.

Static analysis

No suspicious patterns detected.