ClawHub
Back to skill

Security audit

Construction Safety Inspection Checklist

Security checks for vulnerabilities and agentic risk

Overview

This is a plain checklist skill for construction safety inspections and does not include hidden execution, persistence, credential use, or external data access.

Before installing, consider that the skill may activate for broad site-safety questions and then guide a full inspection workflow. Its safety classifications and stop-work language should be reviewed by a qualified supervisor or HSE professional before being treated as official policy or filed as a formal report.

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
  • 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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The trigger list says to activate when the user asks about PPE compliance, housekeeping, or site safety conditions, and also when they mention terms like near miss or incident in a site-wide context. These topics can arise in general safety discussions without the user intending to launch a full 10-category inspection workflow, making the activation boundary too broad.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.