ClawHub
Back to skill

Security audit

无障碍旅行助手

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent Chinese-language accessibility travel guide that mainly returns built-in attraction, hotel, and travel-tip data, with no evidence of exfiltration, persistence, or destructive behavior.

Installers should expect a Chinese-language, China-focused travel information skill with built-in data that may be stale and should be verified with venues before travel. The optional proxy token/network helper is not used by the exposed tools, but the publisher should remove or document it to avoid confusion.

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
  • 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 (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding
The skill declares tools that use an environment token and appear to rely on network-capable access via a proxy token, but it does not define any explicit tool scope such as permissions or allowed-tools. This weakens least-privilege controls and can allow broader-than-expected external access or secret exposure if the runtime grants default capabilities.

Natural-Language Policy Violations

Medium
Confidence
88% confidence
Finding
This markdown file uses Chinese throughout the name, description, examples, and usage guidance, which effectively forces a specific language experience. The policy allows language constraints only when users are given a choice or when the locale limitation is clearly documented and justified, neither of which appears here.

Natural-Language Policy Violations

Medium
Confidence
85% confidence
Finding
The top-level natural-language description is entirely in Chinese and presents the assistant's purpose as serving domestic travel queries, but it does not explicitly state that the skill is China-specific or offer the user a language/locale choice. Under the policy, forcing a specific language without opt-in is a natural-language policy concern.

Static analysis

No suspicious patterns detected.