design-token-generation
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides best practices for design token management and contains only informational content.
- [SAFE]: All external links point to trusted documentation sources including MDN (Mozilla) and the W3C Design Tokens Community Group.
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read and analyze external codebases to identify token drift and raw values.
- Ingestion points: The agent greps the project codebase for raw font-size and line-height values (SKILL.md).
- Boundary markers: No explicit instructions to ignore embedded prompts are provided.
- Capability inventory: The skill does not request or perform any network operations, file writes, or command executions.
- Sanitization: Not applicable as the skill performs read-only analysis for reporting purposes only.
Audit Metadata