frontend-design
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns, hidden instructions, or dangerous commands were detected. The skill is focused on design principles, typography, and user-centric writing.
- [NO_CODE]: The skill does not contain any executable scripts, binaries, or configuration files. It consists solely of instructional documentation and a standard Apache License 2.0 file.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided design briefs, creating a potential input surface. However, the risk is negligible as the agent's capabilities are limited to generating frontend design artifacts and copy, with no access to high-privilege system tools or network operations.
- Ingestion points: Processes a "design brief" and user preferences as described in SKILL.md.
- Boundary markers: None implemented to delimit the brief content from core instructions.
- Capability inventory: Generation of HTML/CSS code and interface copy, and potential use of environment-supported screenshot tools (SKILL.md).
- Sanitization: No validation or sanitization rules are defined for the input content.
Audit Metadata