website-ui-ux-engineer
Pass
Audited by Gen Agent Trust Hub on Mar 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the run_shell_command tool to execute project initialization and build scripts. Evidence includes instructions for npm install and npx create-next-app in the stack setup files.
- [EXTERNAL_DOWNLOADS]: The skill retrieves dependencies and documentation from trusted external sources. Evidence includes the use of official npm packages and fetching guidelines from domains such as w3.org, nextjs.org, and developer.apple.com.
- [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it processes external documentation. 1. Ingestion points: Ingestion occurs through the web_fetch tool as described in maintenance-and-updates.md. 2. Boundary markers: No explicit boundary markers are defined for the fetched content. 3. Capability inventory: The skill can execute shell commands and write to the filesystem. 4. Sanitization: The skill relies on internal evaluation against its design principles rather than automated data sanitization.
Audit Metadata