ClawHub
Back to skill

Security audit

Where We Meet

Security checks for vulnerabilities and agentic risk

Overview

This meetup-planning skill has a coherent purpose, but it relies on an unpackaged local script and sends sensitive location data to Amap without an explicit user notice or confirmation step.

Review before installing. Only use this skill when you are comfortable sharing the provided locations with Amap, prefer approximate landmarks over exact home or work addresses, and verify that the missing scripts/where-we-meet.js implementation is supplied from a trusted source before running it.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill advertises very broad natural-language triggers for location-selection requests without clear activation boundaries, which can cause the agent to invoke it on loosely related prompts that include multiple addresses or meeting language. Because this skill processes sensitive location data and forwards it to external mapping services, overbroad triggering increases the chance of unnecessary disclosure or use in contexts the user did not clearly intend.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill instructs the agent to collect multiple people's addresses and send them to Amap APIs, but it provides no explicit privacy notice, consent step, or data-sharing warning. This is dangerous because home, work, or transit-origin locations are highly sensitive personal data, and users may not realize that third-party geocoding/routing services will receive them.

Content

No source excerpt is available for this finding.