NYC
skills/hairyf/skills/arch-webext-vue/Gen Agent Trust Hub

arch-webext-vue

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE] (SAFE): No malicious patterns or security vulnerabilities were detected in the skill's instructions or configuration files.
  • [Indirect Prompt Injection] (LOW): As a browser extension template, the generated code includes content scripts that execute on third-party websites. This creates an inherent surface for indirect prompt injection if the extension or a connected AI agent processes untrusted data from these pages without further sanitization.
  • Ingestion points: src/contentScripts/index.ts targets all_urls by default.
  • Boundary markers: Absent (Standard web development templates do not typically include LLM-specific delimiters).
  • Capability inventory: The extension uses webextension-polyfill for tab and storage access, and webext-bridge for messaging between background and UI scripts.
  • Sanitization: Uses Vue 3's built-in template escaping for UI rendering.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:20 PM