system-design
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a legitimate workflow for system and component design. It uses standard agent tools such as Read, Write, and Task to perform its functions and adheres to documented boundaries, explicitly avoiding implementation tasks.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input in the form of system requirements and existing codebases which creates a surface for indirect prompt injection.
- Ingestion points: Reads requirements and existing system files via the Read tool and Explore subagent as described in references/system.md.
- Boundary markers: None present; the skill lacks specific delimiters to separate user data from instructions.
- Capability inventory: Includes file reading (Read, Grep), file writing (Write), and subagent delegation (Task).
- Sanitization: No explicit sanitization of ingested content is performed.
Audit Metadata