ClawHub
Back to skill

Security audit

Aerobase Alerts

Security checks for vulnerabilities and agentic risk

Overview

This flight-alert skill is coherent and purpose-aligned, with a privacy note for its local alert-history file.

Before installing, consider that the skill may keep a short local history of recent flight alert activity in ~/alert-history.json. That is useful for avoiding duplicate notifications, but you may want to inspect or delete that file if flight metadata is sensitive. Confirm booking actions before authorizing them.

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
  • 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
93% confidence
Finding
The skill instructs the agent to read and write a persistent workspace file in the user's home directory to track notification history, but it provides no user-facing disclosure, consent boundary, or data-handling constraints. Even though the stated purpose is rate-limit deduplication, persistent local storage can expose travel metadata across sessions, create unintended retention of sensitive itinerary information, and normalize silent statefulness that the user may not expect.

Static analysis

No suspicious patterns detected.