university-coursebook

Pass

Audited by Gen Agent Trust Hub on Sep 23, 2026

Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill directs the agent to use standard shell commands to manage the document lifecycle. This includes creating project directories with mkdir, compiling LaTeX source code using tectonic, and inspecting compilation logs for errors or layout warnings using grep.- [DYNAMIC_EXECUTION]: The skill incorporates dynamic execution of Python code to ensure the accuracy of the generated content. It generates scripts to perform 'hand-calculations' to verify numerical values before they are written into the text and uses a Python script to programmatically count pages in compressed PDF streams.- [INDIRECT_PROMPT_INJECTION]: The skill processes user-defined topics and technical subjects to generate textbooks. While this ingests external input into the agent's workflow, the output is restricted to LaTeX source code. The skill's extensive narrative and formatting rules act as a structural control for the generated content.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 23, 2026, 12:47 PM