k12-lesson-differentiation
Pass
Audited by Gen Agent Trust Hub on Aug 30, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [External Dependency Management]: The skill's rendering process (via
scripts/render_all.sh) manages the installation of thepython-docxlibrary from the official Python Package Index (PyPI). This library is a well-known tool for generating Word documents, which is the skill's primary function. - [Command Execution for Artifact Generation]: The skill utilizes local shell and Python scripts to convert lesson data into classroom-ready materials. This involves standard file system operations and script execution within the agent's environment to produce the final
.docxand.htmlartifacts. - [Data Ingestion Surface]: The skill is designed to ingest external lesson content from files and URLs provided by the user. While this introduces an indirect prompt injection surface (where instructions within a lesson could potentially influence agent behavior), the skill mitigates this by using structured JSON data for rendering and providing specific pedagogical constraints.
- [Dynamic Execution of Local Scripts]: The skill includes several Python scripts that are executed at runtime to handle document formatting and theme application. These scripts are part of the skill's own package and perform deterministic data processing on the generated lesson content.
Audit Metadata