ClawHub
Back to skill

Security audit

Tongcheng

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple travel-summary helper for public Tongcheng/ly.com hotel and flight pages, with no executable code or hidden persistence.

Installers should understand that the skill may activate for Tongcheng-related travel requests and may browse public ly.com pages for summaries; keep its use to explicit hotel, flight, or itinerary comparison tasks and avoid login-only actions, booking, bulk scraping, or attempts to bypass platform checks.

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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The activation description is broad enough to match generic 'Tongcheng-related' requests, which can cause the skill to trigger outside narrowly intended hotel/flight summary use cases. Over-broad invocation increases the chance of unnecessary browsing or data collection behavior being activated in unrelated contexts, expanding the attack surface and creating opportunities for prompt-routing abuse or unintended automation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.