ClawHub
Back to skill

Security audit

China Toys Sourcing

Security checks for vulnerabilities and agentic risk

Overview

This is a China-focused toy sourcing reference skill that reads its bundled data and does not show hidden access, network activity, credential use, or persistence.

Install this if you want a static, China-specific toy industry sourcing reference. Treat the market figures and supplier examples as reference data to verify before business decisions, but the artifacts do not indicate unusual security risk.

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
86% confidence
Finding
The skill is invocable and references code in `do.py` that can read files, but the manifest does not declare any `permissions` or `allowed-tools` scope. That creates an authorization ambiguity: the runtime may grant broader file-read capability than a reviewer or caller expects, which increases the risk of unintended local file access if the implementation changes or is misused.

Natural-Language Policy Violations

Low
Confidence
85% confidence
Finding
The dataset is explicitly framed as "China Toys Industry Overview (2026)" and includes Chinese-language source naming, which imposes a China-specific locale/context. In a skill setting, this can be a natural-language locale policy issue when no user choice or justification is provided in the file itself.

Static analysis

No suspicious patterns detected.