Back to skill

Security audit

Marco Polo Test

Security checks for vulnerabilities and agentic risk

Overview

This is a simple test skill that replies with “polo” when invoked and does not request system access, dependencies, credentials, or background behavior.

Before installing, be aware that ordinary messages containing “marco” may trigger the skill and add “polo” to the assistant response. It is otherwise a minimal, side-effect-free test skill with no disclosed access to local files, credentials, network services, or persistent state.

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
Category
Not specified by scanner
Confidence
97% confidence
Finding

The description says the skill activates whenever a user's message contains the word "marco" as a standalone word or part of a sentence. This is broad enough to overlap with normal conversational text and provides no exclusion conditions or negative examples to limit unintended invocations.

Content

No source excerpt is available for this finding.