ClawHub
Back to skill

Security audit

01 Product Selection

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language business guidance skill for community group-buying product selection, with some adjacent operational advice but no hidden execution, data access, persistence, or privilege behavior.

Review the scope before installing: it is best suited for Chinese-language community group-buying product and pricing analysis, and it includes adjacent operational recommendations that may affect supplier handling, refunds, packaging, and logistics decisions. Treat those as business guidance requiring human approval, not automatic instructions to change live systems.

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 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Description-Behavior Mismatch

Medium
Confidence
95% confidence
Finding
The manifest explicitly says the skill does not include 供应链执行 and 仓储物流, yet the body contains detailed execution-oriented guidance such as supplier blacklisting workflows, supplier backup arrangements, immediate product takedown/refund actions, packaging changes, direct-shipping logistics path changes, inventory/procurement cadence, and warehouse/cold-storage loss analysis. This goes beyond product-selection strategy and pricing into operational execution domains the manifest says are out of scope.

Natural-Language Policy Violations

Medium
Confidence
96% confidence
Finding
The top-level skill description is entirely in Chinese and the rest of the document consistently assumes Chinese-only interaction. Under the policy, forcing a specific language without user opt-in or a clearly documented locale constraint is a natural-language policy violation.

Intent-Code Divergence

Medium
Confidence
96% confidence
Finding
The boundary note states the module focuses only on what to sell and pricing, and that supply chain plus warehousing/logistics are separate with no overlap. Later material contradicts that statement by prescribing cold-storage diagnosis, transport packaging changes, center-warehouse-to-group-leader routing changes, and daily loss monitoring workflows, which are exactly overlapping logistics/warehouse operations.

Static analysis

No suspicious patterns detected.