ClawHub
Back to skill

Security audit

Roofing Knowledge Mentor

Security checks for vulnerabilities and agentic risk

Overview

This skill provides disclosed roofing guidance and contains only an ancillary local validator script with no hidden execution, network access, credential handling, or persistence.

Installers should treat this as domain guidance, not legal, insurance, pricing, or compliance authority. The included validator script is benign local packaging support, but users do not need to run it for normal roofing-advice use.

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 Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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
Findings (4)

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

There is a clear material mismatch. The declared description says the skill provides expert roofing and contractor guidance, reasoning, and business/insurance support. The supplied code does none of that. Instead, it performs repository/skill packaging validation on local files such as SKILL.md, scripts/, references/, and assets/. This is a different primary purpose and introduces undeclared capabilities around filesystem inspection and metadata validation. No roofing-domain logic, estimating logic, operations guidance, or expert decision-making appears in the code.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger guidance is broad and generic, using phrases like basic questions, terminology clarification, why questions, and learning-oriented questions. In an agent system, such open-ended activation criteria can cause the skill to be invoked for many unrelated conversations, increasing the chance of unnecessary context injection, misrouting, or over-application of domain guidance.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The file says to use this reference when the user asks about 'Best workflows,' 'Avoiding mistakes,' or 'Job handoffs,' which are broad phrases without clear boundaries or exclusion conditions. In a markdown skill/reference file, this can cause unintended invocation for general conversations that are not specifically about roofing workflow guidance.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.