scene-structure-techniques
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- General Security Posture (SAFE): The skill is purely instructional and template-based. It provides guidance on the 'Scene-Sequel' writing model and does not include any scripts or commands that interact with the system at a privileged level.
- Indirect Prompt Injection (LOW): The skill accepts user input for scene goals, conflicts, and beats. While it lacks explicit boundary markers to separate user content from instructions, the risk is negligible given the creative writing context and lack of sensitive tool access.
- File System Interaction (SAFE): The skill references saving scene outlines to a
scenes/directory and mentions a/writecommand. These are standard operations for a writing-focused agent and do not target sensitive system files or credentials. - Metadata & Purpose (SAFE): The metadata accurately describes the skill's functionality. There is no evidence of deceptive metadata or hidden instructions.
Audit Metadata