ClawHub
Back to skill

Security audit

🏨 IHG积分房查找

Security checks for vulnerabilities and agentic risk

Overview

This looks like a hotel-points search skill, but its main executable and hotel database are missing or referenced from outside the package.

Install only after the publisher includes the actual query.py and hotels.json files or clearly explains the trusted external path they come from. Treat the backup and rollback scripts as maintenance tools that can change local OpenClaw files, and inspect any backup before restoring it.

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
Confidence
86% confidence
Finding
The skill advertises many broad natural-language triggers such as generic recommendation and query phrases without defining firm activation boundaries, confirmation requirements, or exclusions. In an agent environment, this increases the chance of accidental invocation from ordinary conversation, causing unintended tool execution and data access even though the underlying task is relatively low-risk.

Static analysis

No suspicious patterns detected.