frontend-design
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references and recommends the use of standard, well-known frontend frameworks and styling libraries.
- Dependencies include Astro (v7.3.2), SvelteKit (v2.70.3), Svelte (v5.57.0), Tailwind CSS (v4.3.3), Vite (v8.2.2), Next.js (v16.3.4), React (v19.2.8), and @use-gesture/react (v10.3.1).
- These packages are retrieved from official registries through standard package managers like Bun.
- [COMMAND_EXECUTION]: The instructions include legitimate shell commands for development workflows.
- Typical commands include project initialization (e.g.,
bun create astro@latest), dependency management (bun add), and build verification (bun run build,bun run check). - [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection as it processes external data to generate code.
- Ingestion points:
SKILL.md(Step 1) specifies reading design briefs, existing product guidance, and relevant project files. - Boundary markers: There are no explicit instructions to use delimiters or warnings to ignore embedded commands within ingested data.
- Capability inventory: The skill produces code artifacts (Step 3) and executes build and linting commands (Step 4).
- Sanitization: The instructions do not define specific sanitization or filtering protocols for external content before it is interpolated into code.
- [SAFE]: Comprehensive review of the skill's logic, scripts, and metadata reveals no evidence of obfuscation, credential exfiltration, persistence mechanisms, or unauthorized privilege escalation. The behavior aligns entirely with the stated purpose of a frontend development assistant.
Audit Metadata