architecture-designer
Pass
Audited by Gen Agent Trust Hub on Aug 25, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill is purely instructional and serves as a documentation assistant. It does not request access to sensitive file paths, hardcoded credentials, or network resources. All logic is contained within static Markdown files.\n- [NO_CODE]: The skill contains no executable scripts (Python, Node.js, or shell) or binaries. It relies entirely on the agent's ability to interpret Markdown templates and guidance.\n- [INDIRECT_PROMPT_INJECTION]: The skill has a potential surface for indirect prompt injection as it processes user-provided requirements to generate output.\n
- Ingestion points: User-supplied functional, non-functional, and constraint requirements processed in the Core Workflow (SKILL.md).\n
- Boundary markers: Absent; the instructions do not specify the use of delimiters or boundary instructions for untrusted data.\n
- Capability inventory: Limited to generating Markdown documents and Mermaid diagrams; no system-level capabilities or external API tools are listed in the workflow or reference files.\n
- Sanitization: Absent; the skill does not provide methods for filtering or escaping input data.
Audit Metadata