design-everyday-things
Pass
Audited by Gen Agent Trust Hub on Mar 21, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is primarily documentation-based, providing an instructional framework for the agent to assess user designs using principles like affordances, signifiers, and feedback.
- [PROMPT_INJECTION]: No attempts to override system prompts or bypass safety guidelines were detected. The instructions are focused on design scoring and iterative improvement within the provided framework.
- [EXTERNAL_DOWNLOADS]: The skill contains links to well-known external sources (Amazon) for educational references. No scripts or executable binaries are downloaded or executed.
- [DATA_EXFILTRATION]: No network operations or commands to transmit sensitive data were found. The skill uses standard file discovery tools (Glob, Grep) for local analysis only.
- [COMMAND_EXECUTION]: The skill utilizes a restricted set of tools (Read, Glob, Grep) aimed at project file analysis. No high-risk commands such as subprocess execution or privilege escalation (sudo) are present.
- [NO_CODE]: There are no scripts (Python, JS, Shell) included with this skill; it relies entirely on markdown instructions and agent reasoning.
Audit Metadata