esther-design-system
Warn
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The installation instructions direct the user to clone a repository from a personal GitHub account (esthersjw/esther-design-system) that is not identified as a trusted or well-known vendor.
- [COMMAND_EXECUTION]: The skill's operational workflow requires executing shell commands like 'git clone' and 'cp'. The use of user-provided input to determine the source file path in the 'cp' command creates a potential path traversal or command injection vulnerability if the input is not strictly validated by the agent.
- [EXTERNAL_DOWNLOADS]: The skill references external fonts from Google Fonts (fonts.googleapis.com), which is a well-known and expected service for this functionality.
- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection. (1) Ingestion points: The agent gathers user requirements and content in Step 1. (2) Boundary markers: No delimiters or instructions are provided to the agent to ignore embedded commands in user data. (3) Capability inventory: The agent is instructed to execute shell commands and generate new HTML files. (4) Sanitization: No input validation, escaping, or filtering mechanisms are described for the incoming content.
Audit Metadata