skills/neuroforge-nuxt

Pass

Audited by Gen Agent Trust Hub on Apr 16, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to create a directory named NeuroForge/ and populate it with multiple markdown files (.md). This is part of its documented 'Analysis First' workflow to provide architectural reviews and project documentation.
  • [DATA_EXPOSURE]: The agent is instructed to scan the entire codebase and project structure (including Prisma schemas and existing patterns) to perform its analysis. This is standard behavior for a coding assistant and occurs within the local environment.
  • [PROMPT_INJECTION]: The skill contains strong behavioral framing (e.g., 'Instruction to obey verbatim') to enforce its multi-step workflow. These instructions are used for process control (ensuring analysis happens before code generation) and do not attempt to bypass safety filters or extract system prompts.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 16, 2026, 11:11 AM