ClawHub
Back to skill

Security audit

ly-train-12306

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed train-ticket availability lookup tool that contacts 12306 and does not show hidden credential use, purchasing, or destructive behavior.

Before installing, know that the skill needs internet access to 12306 and may refresh a local station-code cache. It is for checking availability only, does not buy tickets, and does not require login credentials or an API key.

SkillSpector

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
89% confidence
Finding
The skill advertises a network-backed script (`scripts/train_query.py`) and the static analyzer detected file-write and network capabilities, but the manifest does not declare any permissions. Undeclared capabilities are dangerous because they hide the skill's actual trust boundary from reviewers and users, making it easier for a skill to perform unexpected outbound requests or local file modifications without informed consent.

Static analysis

No suspicious patterns detected.