ClawHub
Back to skill

Security audit

interaction-design-sop

Security checks for vulnerabilities and agentic risk

Overview

This skill is a frontend interaction-design checklist with no executable code, credential use, persistence, or hidden data handling.

Installers should expect this skill to make frontend agents more systematic about UI states, confirmations, layout resilience, and implementation readiness. Its scope is broad across frontend interaction work, so users who want narrower activation may prefer tighter routing metadata, but the artifact does not show hidden or unsafe behavior.

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (3)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The skill description contains broad trigger language such as implementing UI views, forms, dashboards, component interaction logic, and frontend UX reviews, which can cause the agent to invoke this skill for a wide range of generic frontend requests. Over-broad activation is dangerous because it can override more specific skills or inject process constraints into unrelated tasks, reducing routing precision and increasing the chance of inappropriate guidance being applied.

Natural-Language Policy Violations

Medium
Confidence
90% confidence
Finding
The prompt text at L06 is written entirely in Chinese and implicitly requires the skill to operate in that language. For a non-region-specific skill, this creates a language policy concern because it does not offer user opt-in or alternative locale handling.

Natural-Language Policy Violations

Low
Confidence
91% confidence
Finding
The prompt at L08 is written entirely in Chinese, which indicates the skill is being evaluated for a specific language context without any visible opt-in, alternative language support, or justification that it is region-specific. Under the language/locale policy, forcing a specific language without user choice is a natural-language policy concern.

Static analysis

No suspicious patterns detected.