token-usage
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides instructions for installing official packages from the
@iress-ossnamespace and references well-known external services for fonts (fonts.googleapis.com) and UI documentation (chromatic.com). These are recognized as legitimate vendor and industry resources. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user queries to generate UI code and provide design guidance, which is a standard surface for indirect prompt injection.
- Ingestion points: User queries regarding design tokens, CSS, or React components as defined in
SKILL.md. - Boundary markers: None specified for separating user-supplied data from system instructions.
- Capability inventory: The skill is primarily used for text and code generation. It does not define or request privileged tools or capabilities (such as shell access or file writes) within the skill context.
- Sanitization: No explicit sanitization or validation of user input is specified.
Audit Metadata