design-interface

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
  • [NO_CODE]: The skill is composed strictly of documentation and prompt templates for agent orchestration. It does not contain or execute any scripts, binaries, or system commands.
  • [PROMPT_INJECTION]: The skill defines a workflow where user-provided input (module descriptions and requirements) is interpolated into prompts for sub-agents, which constitutes a surface for indirect prompt injection.
  • Ingestion points: User-provided module descriptions and requirements collected during the 'Gather Requirements' phase.
  • Boundary markers: No explicit delimiters or boundary markers (such as XML tags or triple quotes) are defined in the prompt template for the sub-agents.
  • Capability inventory: The skill utilizes the 'Task tool' to spawn and manage parallel sub-agents.
  • Sanitization: No input sanitization, escaping, or validation of user-provided strings is implemented within the instruction set.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 09:24 AM