systems-architecture
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [SAFE]: The skill consists of Markdown templates and instructions without executable scripts. It defines best practices for system documentation and includes guardrails against resource exhaustion (Diagram Bombs).
- [INDIRECT_PROMPT_INJECTION]: The skill defines a process for transforming system descriptions into documentation, which involves processing potentially untrusted data about a system's components.
- Ingestion points: Architectural descriptions and system requirements provided as input to the agent (SKILL.md).
- Boundary markers: The instructions mandate clear visual separation (dashed boundaries) for external, untrusted systems.
- Capability inventory: The skill writes to Markdown files and generates Mermaid diagrams (C4_ARCHITECTURE_TEMPLATE.md).
- Sanitization: Relies on default LLM safety filters; no custom input sanitization is implemented.
- [EXTERNAL_DOWNLOADS]: The C4 template references the official documentation for the C4 model at
https://c4model.com, which is a well-known and reputable industry resource.
Audit Metadata