saccoai-frontend-design
Pass
Audited by Gen Agent Trust Hub on Mar 27, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is purely instructional, providing a framework for design thinking and creative direction. It does not contain executable code, shell commands, or network operations.
- [DATA_EXPOSURE]: The skill interacts with local project metadata stored in
.saccoai/directories. This behavior is scoped to the project environment and is consistent with the skill's purpose of interpreting design tokens and site analysis. No access to sensitive system files (e.g., SSH keys, AWS credentials) was found. - [REMOTE_CODE_EXECUTION]: No patterns of remote script downloading or execution were detected. The UI code snippets in the reference files are static examples for layout and styling.
- [PROMPT_INJECTION]: The instructions are focused on guiding the agent's creative output. There are no attempts to bypass safety filters, extract system prompts, or override core agent instructions.
- [COMMAND_EXECUTION]: No shell command invocations or subprocess calls are present in the skill's logic or documentation.
Audit Metadata