frontend-design
Pass
Audited by Gen Agent Trust Hub on Jul 3, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [SAFE]: The skill contains no executable code or external references. It provides high-level design principles and a structured workflow for the agent to follow when assisting with UI design tasks.
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it processes untrusted user-provided design briefs and has the capability to generate code based on that input.
- Ingestion points: User-provided "design brief" referenced in
SKILL.md. - Boundary markers: Absent. No delimiters or warnings are defined to isolate the design brief content from the agent's core instructions.
- Capability inventory: The skill instructs the agent to "write the code" based on the design plan derived from the brief (
SKILL.md). - Sanitization: Absent. There is no instruction to validate or sanitize the content of the user-provided brief before processing.
- [NO_CODE]: The skill consists entirely of instructional markdown and a license file. It does not include any scripts, binaries, or automated configuration files.
Audit Metadata