ClawHub
Back to skill

Security audit

web-artifact-studio

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly a front-end artifact guide, but it contains conflicting and under-scoped instructions about API keys, credentials, external API use, and command execution.

Install only if you intend to use it as a supervised front-end generation guide. Do not provide API keys or credentials to generated artifacts unless you have separately verified the target service and store secrets in proper environment variables; avoid persisting real personal data in localStorage.

SkillSpector

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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 (5)

Description-Behavior Mismatch

Medium
Confidence
93% confidence
Finding
The skill is presented as a front-end artifact generation methodology, but later sections introduce external API usage, authentication failures, token handling, and API connection setup that materially expand its operational scope. This mismatch can mislead users and higher-level agents into granting network/API-related trust or permissions not justified by the declared purpose, increasing the risk of unintended secret handling or external communication.

Intent-Code Divergence

High
Confidence
98% confidence
Finding
The stated 'no extra API key required' guidance conflicts with the later 'first-time setup' workflow that instructs users to configure API keys and establish API connections. In a skill ecosystem, this kind of contradiction is dangerous because it normalizes credential collection in a package that otherwise appears local-only, making phishing-like secret solicitation easier.

Intent-Code Divergence

High
Confidence
98% confidence
Finding
The stated 'no extra API key required' guidance conflicts with the later 'first-time setup' workflow that instructs users to configure API keys and establish API connections. In a skill ecosystem, this kind of contradiction is dangerous because it normalizes credential collection in a package that otherwise appears local-only, making phishing-like secret solicitation easier.

Context-Inappropriate Capability

Medium
Confidence
90% confidence
Finding
The skill advertises broad 'API integration' and 'command execution' capabilities even though its stated purpose is web artifact creation. Overbroad capability claims can cause an agent or user to treat the skill as authorized for generic network access or shell actions, which expands the attack surface beyond what the declared use case justifies.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The example persists user registration data, including email and phone number, in localStorage without privacy warnings, minimization guidance, or retention controls. localStorage is accessible to any script running in the origin and persists across sessions, so storing personal data there increases exposure if the generated artifact later includes XSS or is used on shared devices.

Static analysis

No suspicious patterns detected.