Back to skill

Security audit

Promociones de Viajes Argentina

Security checks for vulnerabilities and agentic risk

Overview

This skill only guides the agent to fetch public Argentina-focused travel promotion data from one disclosed API and present filtered results.

Before installing, expect this skill to contact https://anduin.ferminrp.com for public travel promo data and show deal links. It should not book travel, purchase anything, scrape other sites, create alerts, or use private accounts or credentials.

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 (1)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The skill description is broad enough to match common travel-shopping queries such as flights, hotels, packages, and best daily deals, which increases the chance the agent invokes this skill for generic commerce requests without clear user intent for this specific data source. Over-broad triggering can cause inappropriate tool selection, unnecessary data disclosure to third-party services, and confusion when the skill supplants other more suitable travel or shopping capabilities.

Static analysis

No suspicious patterns detected.