ClawHub
Back to skill

Security audit

Website

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only website best-practices skill with no hidden execution or data access behavior.

This skill is safe to install as general website-building guidance. Users building non-English or multilingual sites should adapt the HTML language guidance to the actual page language rather than defaulting to English.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The instruction "Not setting <html lang="en"> breaks screen reader pronunciation" prescribes English specifically rather than requiring an appropriate page language. This creates a language/locale policy issue because it pushes a fixed locale without user opt-in or a documented region-specific constraint.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.