forge-novel-fusion
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides a set of tools for legitimate fiction writing analysis and style transformation. It relies on local Python scripts to process structured JSON data, which minimizes the risk of unauthorized command execution or data exfiltration.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests style profiles that could be surfaces for indirect prompt injection. This risk is managed by treating the data as abstract prose mechanics and using validation scripts to enforce a strict schema.
- Ingestion points: JSON style profiles loaded from the
novel_styles/directory as specified in the fusion workflow. - Boundary markers: The skill utilizes
L0_style_boundaryandL7_anti_ai_patternssections within the profiles to define stylistic constraints and forbidden AI-like patterns. - Capability inventory: The agent performs file read/write operations and executes the provided Python scripts within the local environment.
- Sanitization: The
scripts/novel_style_validator.pyutility ensures all input and output profiles adhere to the defined schema before they are used in the writing workflow.
Audit Metadata