Back to skill

Security audit

Aerobase Awards

Security checks for vulnerabilities and agentic risk

Overview

The skill is a travel-award search helper whose API, alert, saved-trip, cash-price, and optional logged-in browser behavior are disclosed and aligned with that purpose.

Before installing, expect the skill to use travel itinerary data, award-alert state, transfer-partner or card context, external price lookup, and sometimes airline login sessions you provide. Use it only with accounts and profile data you are comfortable applying to award-search workflows, and confirm alert creation or logged-in airline actions before proceeding.

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
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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
85% confidence
Finding

This is a markdown file, so vague-trigger review applies. The description explains what the skill does but does not specify concrete trigger phrases, activation boundaries, or exclusion conditions, which can make invocation criteria ambiguous in systems that rely on natural-language matching.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

The skill handles potentially sensitive travel-profile data, including saved trips, alerts, and a user's credit card transfer-partner context, without an upfront privacy notice or explicit consent boundary. In an agent setting, this can normalize access to personal data and lead to overcollection, surprise processing, or disclosure of itinerary and financial-profile details beyond user expectations.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.