Back to skill

Security audit

Nearby Beaches

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple nearby-beach lookup guide that uses location data in a disclosed and purpose-aligned way.

Before installing, confirm you are comfortable granting location access for beach searches. The skill should only be used after location permission, and exact coordinates should not be retained beyond what is needed for the lookup.

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
86% confidence
Finding

The trigger conditions are broad enough to activate on general travel or recommendation requests, not just explicit beach lookups. This can cause unintended skill invocation and unnecessary use of precise location context, which increases privacy and routing risk even without malicious intent.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The document is primarily written in Chinese but repeatedly requires English terms like 'Beaches' and 'beach near me' in the usage and trigger descriptions. This can impose a language preference without stating that users may interact in their preferred language or that multilingual input is supported.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.