design-an-interface

Pass

Audited by Gen Agent Trust Hub on Mar 7, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious patterns or executable scripts were identified. The skill is entirely composed of markdown-based design guidelines and prompt templates.
  • [PROMPT_INJECTION]: The skill interpolates user-provided requirements into sub-agent prompts, creating a surface for indirect prompt injection. This surface is considered safe as the skill lacks any dangerous capabilities like network access or file system modification.
  • Ingestion points: User-provided 'module description' and 'gathered requirements' defined in the workflow.
  • Boundary markers: The prompt template uses brackets as placeholders but lacks explicit delimiters or instructions for the agent to ignore embedded instructions.
  • Capability inventory: Employs the 'Task' tool to spawn sub-agents; no network, file-write, or shell execution capabilities are present.
  • Sanitization: No sanitization or validation of user input is implemented.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 7, 2026, 01:40 AM