ClawHub
Back to skill

Security audit

eventbrite-mcp

Security checks for vulnerabilities and agentic risk

Overview

This skill provides read-only Eventbrite query recipes that use an API token or an approved browser bridge, with sensitive account and attendee data access disclosed as part of its stated purpose.

Install only if you are comfortable giving your agent read access to Eventbrite account, order, organization, and attendee data. Avoid logging, sharing, or committing tokens, cookies, attendee emails, order details, or browser-bridge outputs, and use the read-only recipes as written.

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 (3)

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The file explicitly documents using the browser bridge to access session-authenticated account endpoints such as `/api/v3/users/me/orders/` with no accompanying warning that this exposes private user data from the currently signed-in Eventbrite account. In an agent skill context, this increases the chance that an automated workflow queries or reveals personal order history without the user's informed consent, especially because it presents the session-auth path as a convenient fallback when no token is configured.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
This markdown file includes commands that retrieve and display personal data such as the user's email address. The skill description does not include any warning that these examples access account/profile data, which is a privacy-relevant behavior for markdown files.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
These organizer-side examples directly retrieve attendee names and email addresses, which are sensitive personal data, without any warning, minimization guidance, or safer defaults. In a shell/script context, users may casually dump this data to terminals, logs, or downstream tools, increasing the chance of unintended disclosure or misuse.

Static analysis

No suspicious patterns detected.