Back to skill

Security audit

附近取款机

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple nearby-ATM lookup guide with disclosed location use and no executable or persistent behavior.

Before installing, note that this skill uses precise location to find nearby ATMs, so it should only be invoked after you choose to share location. The publisher should narrow the English trigger wording to avoid accidental activation for general banking questions.

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
92% confidence
Finding

The trigger phrase includes the broad English term "cash withdrawal," which can match many banking-related requests that do not specifically ask for nearby ATMs. This can cause the skill to activate inappropriately, leading to incorrect routing of user intent and unnecessary use of location-sensitive functionality.

Content

No source excerpt is available for this finding.