frontend-design
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input in the form of design briefs to generate frontend code, creating a potential attack surface.
- Ingestion points: User-provided design briefs (referenced in
SKILL.md). - Boundary markers: The skill lacks explicit delimiters or instructions to ignore potential commands within the brief.
- Capability inventory: The agent is instructed to generate code (HTML/CSS) based on the input brief.
- Sanitization: There are no instructions for sanitizing or validating the content of the external brief before it is used for code generation.
Audit Metadata