design-consistency-auditor

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill audits frontend codebases by reading project source files and documentation. Content within these files could potentially influence the agent's behavior during the audit process.
  • Ingestion points: TSX, JSX, SCSS, and documentation files within the project directory.
  • Boundary markers: The instructions lack explicit delimiting or warnings to ignore embedded instructions in analyzed files.
  • Capability inventory: The skill uses grep for automated pattern scanning and performs file reads to generate reports.
  • Sanitization: There is no specific process defined to sanitize or filter potential prompts embedded within source code or comments.
  • [COMMAND_EXECUTION]: The skill uses grep for scanning codebases. These commands are executed locally using project paths determined at runtime.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 12:46 AM
Security Audit — agent-trust-hub — design-consistency-auditor