ClawHub
Back to skill

Security audit

Gadget

Security checks for vulnerabilities and agentic risk

Overview

This skill is only a Markdown guide, but its gadget description does not match its location-based venue discovery instructions.

Review this skill before installing if you expect only gadget or smart-home advice. Its instructions may steer an agent toward venue discovery using location, queue, parking, navigation, and reservation-related information, which should be clearly disclosed and user-directed.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill metadata says it provides gadget reviews, smart-home advice, and buying suggestions, but the body describes location-based venue discovery features such as distance filters, queue status, reservations, parking, and navigation. This scope mismatch can cause the agent to invoke the skill in unrelated contexts and route users into unintended location-aware behaviors, which is risky because it changes data expectations and trust boundaries without clear disclosure.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The example prompts are overly broad and generic, such as asking how to use the skill for a 'specific scenario task' or for 'latest玩法/优惠信息', without constraining the domain to gadgets or smart-home topics. Broad activation phrasing increases the chance of unintended triggering and prompt capture from unrelated user requests, which can lead to incorrect tool selection or overreach into tasks the skill was not meant to perform.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

The natural-language description and all user-facing content are presented only in Chinese, with no indication that other languages are supported or that Chinese is an optional locale. Under the policy, a fixed language requirement without user opt-in can be a language/locale policy violation unless clearly justified.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.