ClawHub
Back to skill

Security audit

Ctrip

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Ctrip travel-summary skill with clear limits and no executable code, persistence, credential use, or hidden behavior.

This appears safe to install for public Ctrip travel research. Users should still avoid using it for account actions, bookings, authenticated pages, scraping at scale, or attempts to bypass Ctrip protections.

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
95% confidence
Finding
The description says the skill should be invoked whenever access or automation related to Ctrip is needed, which is broader than the body of the skill actually supports. Overly broad activation can cause the agent to select this skill in inappropriate contexts, increasing the chance of unintended web interaction, policy bypass attempts, or use beyond the stated safe boundaries such as automation against dynamic pages with anti-bot controls.

Natural-Language Policy Violations

Low
Confidence
70% confidence
Finding
The natural-language content of the skill is entirely in Chinese and does not indicate that users may choose another language or that the locale restriction is intentional and justified. Under the stated policy, forcing a specific language without user opt-in can be a natural-language policy violation.

Static analysis

No suspicious patterns detected.