design-system

Pass

Audited by Gen Agent Trust Hub on Oct 27, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from the docs/BRIEF.md file to determine design accents and requirements. If this file contains adversarial instructions, they could influence the agent's code generation and project configuration tasks.
  • Ingestion points: docs/BRIEF.md (Step 1).
  • Boundary markers: None specified for the content of the design brief.
  • Capability inventory: The skill performs file writes to Swift source code in Sources/, creates design/DESIGN-SYSTEM.md, and modifies CLAUDE.md to add persistent project instructions.
  • Sanitization: No sanitization or filtering of the input brief is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 27, 2026, 11:22 PM