design-tokens-sync
Pass
Audited by Gen Agent Trust Hub on Aug 19, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes external, untrusted data from Figma and code repositories, which serves as a potential surface for indirect prompt injection.
- Ingestion points: The skill ingests Figma variable names, types, and values per mode, along with code-side token definitions from connected repositories, JSON/YAML files, and CSS custom properties (SKILL.md).
- Boundary markers: There are no explicit instructions or delimiters defined to ensure the agent ignores or treats embedded instructions within these data sources as plain text.
- Capability inventory: The agent is authorized to read Figma design context, access connected repository files, and create or modify Figma variables in the design file.
- Sanitization: The workflow does not specify any sanitization, validation, or filtering of token names or values before they are used in comparison or variable creation tasks.
Audit Metadata