ClawHub
Back to skill

Security audit

Q Wms

Security checks for vulnerabilities and agentic risk

Overview

This skill is a scoped WMS query helper that routes warehouse questions through q-claw and does not show hidden persistence, code execution, or destructive behavior.

Install this only if you expect the assistant to query your 千易 WMS data through q-claw. Review who can authorize q-claw and what WMS data that authorization exposes, especially inventory, orders, tasks, performance, warehouse, and owner context.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The locale policy states that any locale other than zh_CN or en_US must uniformly fall back to English. This imposes a specific language on users outside those locales without offering choice or opt-in, which matches the language/locale policy violation criteria.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.