frontend-design
Pass
Audited by Gen Agent Trust Hub on Apr 12, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists of instructional markdown files providing design best practices and aesthetic guidelines.
- [PROMPT_INJECTION]: The skill uses authoritative language to define the agent's creative persona and context-gathering workflow, but does not contain instructions to bypass safety filters or reveal system prompts.
- [DATA_EXFILTRATION]: No sensitive file access or network exfiltration patterns were detected. External links are limited to well-known design resources such as WebAIM and Wakamai Fondue.
- [COMMAND_EXECUTION]: The skill does not include any scripts or shell commands. The instruction to use another skill ('teach-impeccable') is a functional workflow requirement for context gathering.
- [SAFE]: Regarding indirect prompt injection risks: the skill ingests data from repository files like project-context/design-context.md and AGENTS.md to establish project context. Ingestion points: SKILL.md. Boundary markers: None explicitly defined. Capability inventory: Frontend code and UI component generation. Sanitization: Not specified. This ingestion is a standard mechanism for project-specific context and is considered safe given the skill's primary purpose.
Audit Metadata