ClawHub
Back to skill

Security audit

小户型装修避坑指南

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only small-apartment renovation advice skill with minor off-topic reference material but no code execution, persistence, or data access.

This skill appears safe to install as a renovation reference aid. Users should treat the advice as general guidance, verify structural/electrical/plumbing decisions with qualified professionals, and ignore any leftover promotional contact details in the source references.

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 (2)

Description-Behavior Mismatch

Low
Confidence
95% confidence
Finding
The reference includes personal contact information and promotional material that is outside the stated scope of small-apartment renovation guidance. In an agent skill, this can cause the system to surface unsolicited contact details or self-promotional content to users, creating privacy, trust, and policy-compliance issues even if there is no direct code execution risk.

Vague Triggers

Medium
Confidence
89% confidence
Finding
The file includes a long, broad keyword recommendation list that appears designed to be clickable or triggerable across many loosely related renovation topics. In an agent skill, overly broad triggers can cause unintended invocation for user queries that only partially match these terms, leading to incorrect routing, noisy activations, or accidental exposure of this skill outside its intended scope.

Static analysis

No suspicious patterns detected.