ClawHub
Back to skill

Security audit

Aerobase Concierge

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent travel concierge, but it asks the agent to act proactively and infer sensitive travel context without clear user consent or boundaries.

Review this skill before installing if you are uncomfortable with a travel assistant making proactive API calls or inferring travel preferences. Confirm that deal monitoring and itinerary guarding only run when you want them to, and avoid providing loyalty or trip details unless you trust Aerobase's data handling.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

High
Confidence
96% confidence
Finding
The skill claims 'autonomous behaviors that activate without being asked' and instructs the agent to act proactively before user requests. In an agent setting, this broad autonomy can cause unauthorized API usage, unexpected actions, and user-surprising behavior, especially when tied to travel monitoring and itinerary-related decisions.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The skill combines proactive monitoring with context tracking but does not disclose what user data is stored, how long it is retained, or when monitoring occurs. This creates privacy and consent risks because sensitive travel patterns, loyalty affiliations, and behavioral preferences may be collected or inferred without clear notice.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The 'User Context Tracking' section explicitly directs persistent tracking of home airport, preferred cabin, loyalty programs, chronotype, upcoming trips, and previously shown deals without any explicit user warning or consent flow. These data points can reveal sensitive travel habits and personal routines, making the issue more serious in a travel concierge context where profile building is central to operation.

Static analysis

No suspicious patterns detected.