skills/fusengine/agents/laravel-blade/Gen Agent Trust Hub

laravel-blade

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [Prompt Injection] (LOW): The SKILL.md file contains an 'Agent Workflow (MANDATORY)' section that instructs the agent to use specific tools like TeamCreate and spawn additional specialized agents such as fuse-ai-pilot before performing any implementation tasks. This is an attempt to override the agent's default operational procedures using authoritative language.
  • [External Downloads] (LOW): Multiple templates, including references/templates/AdvancedDirectives.blade.md and references/templates/LayoutComponent.blade.md, reference external CSS and JavaScript assets from non-whitelisted sources such as cdn.jsdelivr.net and fonts.bunny.net. While standard in web development, these represent external dependencies outside of the skill's immediate environment.
  • [Dynamic Execution] (SAFE): The skill provides documentation for creating custom Blade directives and components which involve runtime compilation into PHP. These are standard architectural features of the Laravel framework and follow established security practices, such as escaping output by default.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:15 PM