frontend-css-patterns
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to run
npx design-md, which downloads and executes a third-party Node.js package from the npm registry. This represents a dependency on external code that is not versioned or verified within the skill context. - [COMMAND_EXECUTION]: The skill uses the
npxcommand-line tool to perform design token exports, representing the execution of external logic within the environment. - [INDIRECT_PROMPT_INJECTION]: The skill is configured to ingest data from external project files (
DESIGN.mdand YAML frontmatter) to generate CSS properties, which creates a potential surface for injection. - Ingestion points: The skill reads design tokens and configuration data from external markdown and YAML files.
- Capability inventory: The skill generates CSS code and has the capability to execute shell commands via
npx. - Boundary markers: There are no explicit instructions or delimiters provided to ensure the agent ignores or sanitizes malicious instructions that might be embedded within the project files.
- Sanitization: No specific validation or filtering logic is defined for the external tokens before they are interpolated into the generated CSS output.
Audit Metadata