better-colors
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill establishes an auditing workflow that requires the agent to ingest and analyze external codebase files to identify color literals and token usage.
- Ingestion points: The instructions guide the agent to collect color literals from the project using grep for patterns like hex, rgb(, hsl(, and oklch( as detailed in
palette-structure.mdandSKILL.md. - Boundary markers: No explicit delimiters or instructions to ignore embedded commands in the processed data are provided.
- Capability inventory: The skill is capable of suggesting and applying modifications to color definitions and token assignments across the project's CSS and component files as seen in the 'Before you finish' section of
SKILL.md. - Sanitization: No specific sanitization or escaping of external content is mentioned.
- Note: This ingestion surface is fundamental to the skill's primary purpose as a color system auditor, and the risk is assessed as negligible due to the highly structured nature of the target data (color notation).
Audit Metadata