interface-design

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface.
  • Ingestion points: User-provided descriptions of 'Intent' and 'Domain Exploration' data (SKILL.md).
  • Boundary markers: No explicit delimiters or system instructions are present to ensure the agent ignores potential embedded commands within the user-supplied design requirements.
  • Capability inventory: The skill directs the agent to create and update local files, specifically docs/design-system/interface-system.md, based on user interaction.
  • Sanitization: There is no evidence of input validation or sanitization before user-provided content is interpolated into the design system documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 08:38 AM