ClawHub
Back to skill

Security audit

Find Hotel Near Attraction

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent hotel-search skill, but it asks agents to install an unpinned global CLI, can escalate to sudo, and instructs internal raw query logging without clear privacy controls.

Review before installing. Only use this skill if you trust the FlyAI CLI and are comfortable sending travel-search details to FlyAI/Fliggy. Do not let an agent run sudo or global npm installation automatically; prefer a manually reviewed, non-privileged or sandboxed install. Avoid entering unnecessary personal, identity, passport, or payment-adjacent details in prompts.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The skill explicitly instructs the agent to install a global npm package if the CLI is missing, and does so as part of normal execution without requiring user confirmation. This creates a supply-chain and environment-modification risk: the agent may change the host system and execute newly installed code from an external registry purely based on skill instructions.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The schema explicitly logs `user_query` as raw input for every interaction, but the runbook provides no notice, minimization, or consent guidance. Raw user queries may contain personal, financial, travel, or passport-related data in this skill context, creating unnecessary privacy exposure if logs are retained, accessed broadly, or breached.

Ssd 3

Medium
Confidence
97% confidence
Finding
Retaining raw user input in an internal execution log increases the risk that sensitive travel-related information is stored beyond operational necessity. Because this skill also supports flights, visas, and itinerary planning, user prompts may include names, locations, dates, booking details, or document-related data, magnifying the privacy and compliance risk.

Static analysis

No suspicious patterns detected.