ClawHub
Back to skill

Security audit

iaiops-warehouse

Security checks for vulnerabilities and agentic risk

Overview

This warehouse operations skill is mostly purpose-aligned, but it claims to be read-only while documenting industrial write and publish actions that need careful review.

Install only if you intend to use it for warehouse automation or OT diagnostics and can enforce approval controls for write actions. Treat it as a read-first but not read-only skill, and verify that write/publish tools are blocked or separately approved in your environment.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (4)

Description-Behavior Mismatch

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The manifest explicitly claims the warehouse edition is read-only, but the documented toolset includes write-capable and publish-capable operations such as eip_write_tag, profinet_dcp_set, mqtt_publish, uns_publish, and stream_publish. This mismatch can cause users, orchestrators, or policy engines to authorize the skill under a false safety assumption, creating a path to unintended control changes or outbound data actions in industrial environments.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The description says to use the skill whenever a task mentions terms like "warehouse," "logistics," "distribution center," or "material handling." Several of these are broad business terms that can appear in many ordinary conversations, and the file does not provide negative examples or tighter scope boundaries for when the skill should not activate.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

Nearly all user-facing instructional content after the header is written in Chinese, but the file does not state that the skill is region-specific or that users may choose another language. This creates a locale policy issue because the skill effectively enforces a specific language without documented opt-in or justification.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The workflow text says the edition is read-priority and forbids unauthorized writes, but that is weaker than the manifest's 'read-only' claim and confirms writes are actually possible. In practice, this inconsistency can mislead operators into trusting the skill as non-invasive while hidden write paths remain available behind procedural language such as approval or MOC.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.