recipe-front-design
Pass
Audited by Gen Agent Trust Hub on Mar 13, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill follows an orchestration pattern where user-provided requirements and file paths are interpolated into prompts for sub-agents, creating a surface for indirect prompt injection.
- Ingestion points: User requirements ($ARGUMENTS) and prototype code paths provided in SKILL.md.
- Boundary markers: Absent; user input is placed directly into the task description for the sub-agents.
- Capability inventory: Invokes external sub-agents (requirement-analyzer, ui-spec-designer, etc.) via the Task tool.
- Sanitization: Absent; the skill relies on the specialized sub-agents to interpret the data correctly as intended for its primary role as a coordinator.
Audit Metadata