design-an-interface

Pass

Audited by Gen Agent Trust Hub on Jun 18, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface where user-provided data is passed to sub-agents.
  • Ingestion points: User input for module descriptions and requirements enter the context in SKILL.md.
  • Boundary markers: The skill lacks delimiters or explicit instructions to ignore commands embedded within interpolated user data.
  • Capability inventory: The skill spawns multiple sub-agents via the Task tool to interpret and act on provided requirements.
  • Sanitization: No validation or escaping is applied to user input before sub-agent processing.
  • [NO_CODE]: The skill consists entirely of markdown-based instructional prompts and contains no executable scripts or code files.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 18, 2026, 08:31 AM
Security Audit — agent-trust-hub — design-an-interface