ClawHub
Back to skill

Security audit

China Home Appliances Factory

Security checks for vulnerabilities and agentic risk

Overview

This skill is a static China home-appliances sourcing guide that only reads its bundled data file and does not show hidden access, persistence, or destructive behavior.

This appears safe to install from a security perspective. Treat the industry figures and sourcing advice as static reference data rather than verified live market intelligence, and independently verify suppliers, certifications, and regulatory requirements before making purchasing decisions.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Lp3

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding
The skill advertises itself as invocable but does not declare any explicit tool scope or permissions, while static analysis detected file-read capability in the implementation. This creates a trust and containment gap: users and reviewers cannot tell from the manifest what local file access the skill may perform, which can enable unintended data exposure if the runtime grants broader access than expected.

Natural-Language Policy Violations

Low
Confidence
80% confidence
Finding
This JSON file includes Chinese text within otherwise English content, such as source names on L004. For all file types, language-policy issues should be flagged when a skill or data artifact imposes or assumes a language without user opt-in or documented justification; here no locale scope or language-selection context is provided.

Static analysis

No suspicious patterns detected.