ClawHub
Back to skill

Security audit

Site Architecture

Security checks for vulnerabilities and agentic risk

Overview

This skill is a markdown-only website planning aid with no hidden execution, persistence, credential access, or destructive behavior.

Install this if you want an agent to help plan website structure, navigation, URLs, and visual sitemaps. Be aware it may read local product-marketing context files if present, and schema implementation should still be handled by a dedicated structured-data skill.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The manifest description says 'When the user wants to plan, map, or restructure their website's page hierarchy' and later 'Use this whenever someone is planning what pages a website should have and how they connect.' Those conditions are broad natural-language triggers for a markdown/manifest file and do not provide narrow constraints or negative examples beyond a few excluded adjacent skills, increasing the chance of unintended invocation.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

This JSON eval file is a manifest-like file, so vague-trigger checks apply. The expected behavior explicitly says 'Should trigger on casual phrasing,' and the paired prompt is a broad everyday question about URL structure, which suggests activation on loosely scoped natural language rather than a specific invocation boundary.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The manifest explicitly says this skill is not for structured data and directs schema-related work to a separate schema-markup skill. However, the file provides concrete breadcrumb schema markup examples in both microdata and JSON-LD, which is a capability not justified by the stated scope of planning site hierarchy and navigation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.