style-library
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions to run local Node.js scripts (new-style.mjs and build-registry.mjs) for managing the style library and building the registry.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests content from external files that may contain untrusted data.
- Ingestion points: The skill reads and processes content from style-library/registry.json, DESIGN.md, tokens.css, and the style-templates/ directory.
- Boundary markers: There are no specific delimiters or safety instructions provided to the agent to distinguish ingested data from instructions.
- Capability inventory: The skill has command execution capabilities through the use of local Node.js scripts.
- Sanitization: The instructions do not specify any sanitization or validation of the content read from the external files.
Audit Metadata