ClawHub
Back to skill

Security audit

12306

Security checks for vulnerabilities and agentic risk

Overview

This is a small 12306 rail-travel helper skill with disclosed account-data handling guidance and no executable code or hidden install behavior.

Install only if you want help with official 12306 ticket, waitlist, or order-summary workflows. Because the skill may work with login sessions, passenger names, ID tail numbers, and order status, keep actions user-directed and avoid storing or sharing more personal travel data than needed.

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
  • 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 (2)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The invocation text says the skill should be called whenever a user needs to access or automate anything related to 12306, which is broader than the narrowly defined compliant use cases in the rest of the file. Over-broad routing can cause the agent to invoke this skill for loosely related requests, increasing the chance of unnecessary handling of login state, ticketing workflows, or personal travel data in contexts where a more limited or safer tool should be used.

Natural-Language Policy Violations

Low
Confidence
72% confidence
Finding
The skill's natural-language description and operating instructions are entirely in Chinese and implicitly assume a Chinese-language interaction context, but there is no statement offering the user a language or locale choice. Under the policy, locale or language constraints should be opt-in or clearly documented as justified.

Static analysis

No suspicious patterns detected.