faq-page
Pass
Audited by Gen Agent Trust Hub on Jul 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates as a code generator for a user interface component. It does not perform any network requests, access sensitive local files, or execute system commands.\n- [PROMPT_INJECTION]: The skill processes external data from a user-provided brief and a design file, representing an indirect prompt injection surface. This is assessed as safe as the skill lacks dangerous capabilities that could be exploited.\n
- Ingestion points:
DESIGN.mdand the user-provided project brief.\n - Boundary markers: Output is delimited by
<artifact>tags, but no specific input delimiters are instructed.\n - Capability inventory: No subprocess calls, file-write operations, or network functions are present in the skill or the provided example.\n
- Sanitization: None detected, as input content is treated as text for UI template generation.
Audit Metadata