frontend-design
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill consists entirely of markdown instructions and metadata. There are no scripts (Python, JavaScript, shell) or binaries included in the distribution.
- [EXTERNAL_DOWNLOADS]: The skill references Anthropic's official GitHub repository as its source upstream. These are documentation links for provenance and do not trigger automated downloads or remote code execution.
- [PROMPT_INJECTION]: The instructions use standard natural language directives to guide the AI's creative output. No attempts to bypass safety filters, extract system prompts, or override agent constraints were detected.
- [INDIRECT_PROMPT_INJECTION]: While the skill processes user-supplied frontend requirements, it lacks any tool-based capabilities (like file writes or network access) that could be exploited via malicious input. The attack surface is effectively zero.
Audit Metadata