ClawHub
Back to skill

Security audit

Match a website's brand and design tokens

Security checks for vulnerabilities and agentic risk

Overview

This skill coherently helps an agent extract colors, fonts, and design tokens from a website using the MiroMiro API, with no hidden persistence or local code execution found.

Install only if you are comfortable using MiroMiro as a third-party service for website analysis. Treat submitted URLs as shared with that service, do not use private/internal sites unless intended, and provide your own MiroMiro API key rather than embedding someone else's key in project files.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

This markdown file includes invocation guidance, so SQP-1 applies. The phrase "match our brand" is generic and the description provides multiple broad examples, but no negative examples or explicit boundaries for when the skill should not trigger, which could lead to unintended activation.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill instructs the agent to send a user-supplied URL to a third-party API, but it does not require an explicit disclosure that the target URL will be transmitted to an external service. This can create privacy and confidentiality risks, especially if users provide internal, staging, or otherwise sensitive URLs assuming analysis will occur locally.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.