backend-architect
Pass
Audited by Gen Agent Trust Hub on Aug 1, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill contains only markdown-based instructions for architectural design. No executable scripts, binaries, or suspicious commands are included in the skill package.
- [PROMPT_INJECTION]: The skill defines a workflow to process user-supplied domain context and requirements, creating a surface for indirect prompt injection. Evidence chain: (1) Ingestion points: User-provided use cases and non-functional requirements; (2) Boundary markers: Absent; (3) Capability inventory: The skill instructions do not grant access to shell execution, network tools, or file system modifications, limiting the agent to generating text and diagrams; (4) Sanitization: Absent. The lack of actionable tools or dangerous capabilities reduces this risk to a safe level.
Audit Metadata