ClawHub
Back to skill

Security audit

Construction

Security checks for vulnerabilities and agentic risk

Overview

This is a plain Markdown construction-management skill with no executable code, network behavior, persistence, or hidden authority, though users should handle project, safety, personnel, and financial records carefully.

Install only where project records may be handled by authorized users. Treat incident reports, worker names, visitor logs, photos, budget data, change orders, and disputes as confidential, and review or redact owner/client communications before distribution.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Confidence
93% confidence
Finding
The manifest description says to 'Use for construction and project management operations' and then lists a very wide range of activities without clear trigger boundaries or exclusion conditions. This makes activation criteria ambiguous because many ordinary project-management conversations could plausibly match.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill directs collection of sensitive operational and personal data such as visitor identities, incident details, photos, witnesses, and employer/trade information without any minimization, access control, retention, or privacy guidance. In a real deployment, this can lead to unnecessary exposure of personal data, safety records, and potentially legally sensitive incident information to unauthorized users or systems.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The client/owner reporting and communication logging sections encourage broad external sharing of financial status, safety summaries, RFIs, action items, and communications without classification or need-to-know controls. That creates a realistic risk of disclosing confidential project, personnel, dispute, or safety information to parties who should receive only sanitized or contractually permitted subsets.

Static analysis

No suspicious patterns detected.