ClawHub
Back to skill

Security audit

Rau — 前端全栈AI时代工程心智

Security checks across malware telemetry and agentic risk

Overview

This is a text-only front-end engineering persona skill with broad activation phrases but no code, credential access, file access, network behavior, or persistence.

Install this if you want an opinionated Rau-style front-end engineering advisor. Be aware it may activate on common web-development terms, and treat the named-persona framing as stylistic guidance rather than official advice from the referenced people.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (2)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The trigger phrases are broad, generic frontend terms such as React, Next.js, 性能优化, and 开发者体验, which are likely to appear in ordinary conversation. This can cause unintended activation of the skill and lead to prompt/context hijacking of unrelated sessions, especially because the skill strongly steers persona and response style once activated.

Vague Triggers

Medium
Confidence
89% confidence
Finding
The invocation examples include common phrases like '性能优化', '开发者体验', and '这个React组件怎么设计', which overlap heavily with routine frontend requests. In context, this makes accidental triggering more likely and increases the chance that the skill's behavioral instructions override the user's intended framing in normal technical discussions.

VirusTotal

52/52 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.