ClawHub
Back to skill

Security audit

Tabussen

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward transit-planning skill that runs local helper scripts to query the ResRobot public transport API and shows no hidden or destructive behavior.

Install only if you are comfortable providing a ResRobot/Trafiklab API key and sending transit searches to ResRobot. Use a dedicated API key, keep it out of shared logs, and make sure curl and jq are available before using the skill.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Lp3

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding
The skill instructs the agent to invoke local shell scripts (`./search-location.sh`, `./journey.sh`) but does not declare any permissions or execution constraints. Undeclared shell capability increases the risk of unexpected command execution, makes trust boundaries unclear, and can enable injection or unsafe execution if later script implementations interpolate user input unsafely.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.