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