brand-visual-language
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of data from external, potentially untrusted live websites to extract brand identity and design tokens.\n
- Ingestion points: External DOM content and computed styles retrieved via
get_brand_identityandget_design_tokenstools mentioned in theSKILL.md.\n - Boundary markers: The instructions do not specify any delimiters or warnings to ignore instructions embedded within the target website's metadata or content.\n
- Capability inventory: The skill is designed to work with tools that read DOM data and potentially write or update design tokens in CSS, SCSS, or configuration files (e.g.,
tailwind.config.*).\n - Sanitization: No explicit sanitization or validation of the retrieved DOM data is described before it is processed by the agent to establish design patterns.
Audit Metadata