ClawHub
Back to skill

Security audit

SRT

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed SRT train-booking helper, but users should treat it as access to a real travel account.

Install only if you are comfortable giving the skill your SRT account credentials and allowing it to make or cancel reservations on your behalf. Use a private Discord channel for monitoring reports, keep log and PID files in a private home or temp directory, and verify train, reservation, and cancellation details before running commands.

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
95% confidence
Finding
The skill clearly requires sensitive environment variables, shell execution, and read/write access to local files, yet it declares no permissions. This creates a trust and review gap: users or platforms may approve the skill without understanding that it can access credentials, persist data, launch background processes, and modify cron-managed state. In a booking skill handling account credentials and reservation logs, undeclared capabilities materially increase security risk.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.