deep-think
Pass
Audited by Gen Agent Trust Hub on Feb 15, 2026
Risk Level: LOWNO_CODE
Full Analysis
- NO_CODE (SAFE): The skill is composed entirely of Markdown documentation and descriptive text files. It lacks any executable scripts (Python, JavaScript, Shell) or configuration files that trigger tool execution.
- PROMPT_INJECTION (SAFE): While the skill provides high-level instructions on how the agent should approach tasks ('Craftsman Mode'), these instructions are focused on software design principles and do not attempt to bypass safety guards or extract system prompts.
Audit Metadata