create-component-md
Pass
Audited by Gen Agent Trust Hub on May 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local shell commands to manage workspace directories and perform data validation.
- Evidence: Uses
mkdirfor recursive directory creation andnode figma-plugin/scripts/validate-base.mjsfor JSON schema validation. - [PROMPT_INJECTION]: The skill processes untrusted JSON data extracted from a Figma plugin, which represents an indirect prompt injection surface.
- Ingestion points: Ingests data from
_base.json(at a user-defined path) anduspecs.config.json. - Boundary markers: Data processing is constrained by expected JSON keys and structured schema definitions.
- Capability inventory: File system read/write access and shell execution capabilities for project management.
- Sanitization: Implements mandatory validation using the Ajv library to ensure input data conforms to a strict schema before interpretation begins.
Audit Metadata