ClawHub
Back to skill

Security audit

festival-flight

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent flight-search integration, but it tells agents to install an unpinned global npm CLI automatically without a clear user approval boundary.

Review before installing. Only use this skill if you are comfortable sending travel search details to the flyai/Fliggy CLI, and require manual approval for any npm install. Prefer a pinned or isolated install instead of allowing an agent to modify the global npm environment automatically.

SkillSpector

Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill explicitly directs the agent to install a global npm package and execute a CLI as a mandatory prerequisite, but provides no user-consent boundary, sandboxing guidance, or warning that this changes the host system and may run untrusted code. In an agent environment, this can lead to unauthorized package installation, arbitrary code execution via npm lifecycle scripts, and persistent modification of the machine.

Static analysis

No suspicious patterns detected.