ClawHub
Back to skill

Security audit

参考网站改 UI：抓设计 token 再落地

Security checks for vulnerabilities and agentic risk

Overview

This skill is a narrow, disclosed workflow for fetching public website CSS design tokens and applying them to local UI styling.

Install if you want a Chinese-language workflow for extracting CSS design tokens from a reference website. Use it only on URLs you intentionally provide, avoid private or internal addresses, and review any generated token output or stylesheet edits before committing them.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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
Findings (3)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
86% confidence
Finding

The skill instructs the agent to perform network access (curl, urllib fetches to arbitrary user-provided URLs) and local file writes (--json out.json, modifying local stylesheets) but does not declare any tool scope or allowed-tools restrictions. This can lead to over-broad execution authority, making SSRF-like internal fetches, unexpected outbound requests, or unintended file modifications more likely if the skill is invoked on untrusted input.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The manifest title and description are entirely written in Chinese and frame invocation around Chinese user phrasing, without offering any language choice or noting that the skill is Chinese-only. This creates a natural-language locale constraint that is not documented as optional or justified as region-specific.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
97% confidence
Finding

The HTTP request hard-codes Accept-Language: en-US,en;q=0.9, which imposes an English/US locale preference regardless of the user's actual language or environment. This is a natural-language/locale policy concern because the script does not offer opt-in, configuration, or justification for the forced locale.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.