sketch
Pass
Audited by Gen Agent Trust Hub on Sep 1, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill utilizes external resources including the Tailwind CSS framework via a public CDN (https://cdn.tailwindcss.com) and references the get-shit-done-cc utility via npx commands.
- [COMMAND_EXECUTION]: The skill instructions involve executing shell commands to manage directories and files (mkdir, write_file). It also uses browser automation tools (browser_navigate and browser_vision) to render and inspect the generated UI variants on the local file system.
- [INDIRECT_PROMPT_INJECTION]: The skill has an ingestion surface for untrusted data as it processes user-provided adjectives and design references to generate code. 1. Ingestion points: User input for design 'Feel', 'References', and 'Core action' in SKILL.md. 2. Boundary markers: Absent; user input is interpolated into HTML files without explicit delimiters or instructions to ignore embedded commands. 3. Capability inventory: The skill can write local files and execute browser navigation and vision tools. 4. Sanitization: Absent; the skill does not explicitly sanitize or escape user-provided strings before including them in the generated source code.
Audit Metadata