ClawHub
Back to skill

Security audit

Where We Meet

Security checks for vulnerabilities and agentic risk

Overview

The skill matches its meeting-place purpose, but it asks the agent to run a local JavaScript file that is not included in the package while handling people’s addresses and map API keys.

Review before installing. The main risk is not clear malicious behavior, but packaging and containment: the skill tells the agent to run a relative local Node script that is not included in the artifact, and it processes sensitive location data plus an Amap API key. Install only if you know where the script will come from, can verify that script, and are comfortable with generated QR/HTML/request files being created locally.

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (1)

Vague Triggers

Medium
Confidence
87% confidence
Finding
The skill advertises very broad natural-language triggers such as general 'where should we meet' and multiple Chinese variants, but does not define firm activation boundaries or exclusions. This can cause the agent to invoke the skill for loosely related location or planning requests, increasing the chance of inappropriate tool execution, unintended data handling, or user confusion about why a location-processing workflow was triggered.

Static analysis

No suspicious patterns detected.