design-consistency-auditor

Pass

Audited by Gen Agent Trust Hub on Apr 10, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides various grep commands to search the local workspace for design system violations, such as hardcoded hex colors (e.g., #[0-9a-fA-F]\{6\}) and arbitrary Tailwind values (e.g., bg-\[#).
  • [PROMPT_INJECTION]: The skill is designed to ingest and process untrusted local source code, creating a surface for indirect prompt injection.
  • Ingestion points: Local application source code files (.tsx, .jsx) discovered in the apps/ directory (SKILL.md).
  • Boundary markers: No specific delimiters or instructions to ignore embedded content are provided for the code reading phase.
  • Capability inventory: Utilizes grep for pattern discovery and standard file system read access to analyze components (SKILL.md, references/full-guide.md).
  • Sanitization: The instructions do not define sanitization or validation routines for the content found within the analyzed files.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 10, 2026, 09:45 AM