ClawHub
Back to skill

Security audit

网红景点

Security checks for vulnerabilities and agentic risk

Overview

This is a simple travel-guidance skill for internet-famous attractions, with only a minor scope-breadth note and no security-impacting behavior found.

Before installing, note that this skill may activate for broad requests about planning trips to popular attractions. It appears safe and lightweight, but users who want tighter routing should narrow its trigger wording to explicit requests about 网红景点 or social-media check-in routes.

A.I.G

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

SkillSpector

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

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

The description says the skill is invoked when users search for internet-famous attractions or plan related travel, but it does not define clear boundaries for when this skill should activate versus a general travel or itinerary skill. The lack of explicit constraints or exclusion examples could cause unintended invocation on broad travel queries.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.