The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill utilizes npx to execute style-dictionary and terrazzo. These are well-known industry-standard tools for design token transformation and validation. The use of npx implies a runtime download of these packages from the npm registry.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and parse external token files (JSON, YAML, JS, CSS). This creates an attack surface where malicious instructions could be embedded in token properties like $description or custom metadata. However, the skill's instructions focus strictly on structural and schema validation, which significantly mitigates the risk of the agent acting on embedded content.
Ingestion points: Token files are read and parsed in Step 2 and Step 3.
Boundary markers: The skill does not define explicit delimiters to separate token content from instructions, but it uses a rigid validation framework.
Capability inventory: The skill has access to file reading, writing, and scoped bash commands (cat, ls, npx).
Sanitization: No specific sanitization of token values or descriptions is mentioned before they are processed for the validation report.

schema-validator