create-prompt
Pass
Audited by Gen Agent Trust Hub on Feb 18, 2026
Risk Level: SAFE
Full Analysis
- [Indirect Prompt Injection] (SAFE): The skill defines a process for creating prompt templates using Mustache-style placeholders. This creates a surface for indirect injection if used with untrusted runtime data.
- Ingestion points: prompts/*.md.
- Boundary markers: Absent.
- Capability inventory: Instructional only.
- Sanitization: Absent.
- [Command Execution] (SAFE): Instructions include the use of 'dzx' CLI tools for validation and building. These are standard development tools for the target environment.
Audit Metadata