long-arc-planning
Pass
Audited by Gen Agent Trust Hub on Jun 29, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a legitimate workflow for script structure planning, utilizing MCP tools for state management and validation. All operations, including artifact loading (
load_artifact) and state updates, are confined to the defined project directory (projects/<slug>/state/).- [SAFE]: Analysis of the data ingestion surface (load_artifact("characters")) confirms that while external content is processed, the skill's restricted capabilities—limited to JSON output and decision logging—preclude any significant indirect prompt injection risk. Output is subject to schema validation, ensuring data integrity.
Audit Metadata