esther-design-system
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the AI agent to manage local files by copying internal templates to an output file using standard shell commands (e.g.,
cp). This is an expected behavior for a template-based design tool. - [EXTERNAL_DOWNLOADS]: The documentation references an external GitHub repository for the design system's source code and assets. As GitHub is a well-known service, this reference is considered safe.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided content such as text and media to populate generated HTML templates.
- Ingestion points: User-supplied content (text, images, video) provided during Step 1 of the workflow (gathered in
SKILL.md). - Boundary markers: Not explicitly defined in the provided file.
- Capability inventory: The skill has the capability to write and output HTML files, potentially including embedded CSS and JavaScript for visual effects.
- Sanitization: The skill does not explicitly describe sanitization for user-provided strings; however, the risk is minimal and restricted to the context of the generated web output.
Audit Metadata