ClawHub
Back to skill

Security audit

China-Apparel & Accessories Factory

Security checks for vulnerabilities and agentic risk

Overview

This skill is a static China apparel sourcing reference and its code only reads its bundled data file.

Reasonable to install for static sourcing guidance. Treat business claims, 2026 projections, certifications, and any supplier contact details as leads to verify independently before making purchasing decisions; no evidence of local data collection or external transmission was found.

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)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
85% confidence
Finding

The skill is marked invocable and references code in run.py with detected file_read capability, but it declares no explicit permissions or allowed-tools scope in the manifest. This creates an authorization ambiguity where the runtime may grant broader file access than users or reviewers expect, increasing the risk of unintended local file disclosure if the implementation reads beyond its intended data files.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

The top-level docstring frames the skill as specifically for 'China apparel and accessories industry intelligence,' which imposes a geographic/locale constraint in natural language. Because the file does not offer an alternate locale choice or explain that the restriction is a required regional-compliance context, this may conflict with the policy against forced locale constraints without opt-in.

Content

No source excerpt is available for this finding.