ClawHub
Back to skill

Security audit

Style Guide Generator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward style-guide generator that analyzes user-provided design materials and does not show hidden persistence, credential access, destructive behavior, or unrelated data handling.

Before using this skill, avoid giving it private intranet pages, authenticated URLs, or sensitive documents unless you intend the agent to inspect that content for style-guide generation. Expect it to analyze provided websites and design materials and produce a structured PDF-style guide.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly instructs the agent to fetch and analyze user-provided URLs, but it does not require notifying the user that external content and URLs will be sent to a web-fetching tool. This creates a privacy and data-handling risk because users may provide internal, sensitive, or authenticated links without understanding that the agent will access them through an external tool or service.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.