mission-blueprint-compiler
Pass
Audited by Gen Agent Trust Hub on Apr 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is entirely instructional, focusing on best practices for prompting and workflow orchestration. It does not contain executable scripts or commands that interact with the host system.
- [PROMPT_INJECTION]: The meta-prompt template provided for generating blueprints uses direct interpolation for user-supplied objectives and constraints. This is an inherent property of orchestration design skills and does not represent a malicious injection, though it creates a surface for indirect prompt injection if user-provided content contains instructions to subvert the resulting blueprint's logic.
- Ingestion points:
SKILL.md(Objective and Constraints placeholders). - Boundary markers: Uses markdown-style headers to delineate input sections.
- Capability inventory: The skill is restricted to text generation; it has no file-write, network, or subprocess capabilities.
- Sanitization: No explicit sanitization logic is included, which is standard for purely instructional prompting skills.
Audit Metadata