textbook-to-presentation-generator

Pass

Audited by Gen Agent Trust Hub on Jul 27, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill downloads the pptxgenjs library from the public NPM registry to enable slide generation functionality.
  • [COMMAND_EXECUTION]: The workflow involves executing several shell commands, including npm install for dependency management, node generate.js to run the locally generated presentation script, and python -m markitdown to verify the output.
  • [PROMPT_INJECTION]: The skill processes untrusted external data from textbook files and feedback, creating a surface for indirect prompt injection.
  • Ingestion points: Reads chapter files from docs/chapters/ and student feedback from input-knowledge/ (SKILL.md).
  • Boundary markers: No delimiters or instructions to ignore embedded commands are present in the processing logic.
  • Capability inventory: The skill can write files to the project directory and execute local Node.js and Python scripts (SKILL.md).
  • Sanitization: No specific validation or filtering of the ingested textbook content is performed before it is used in the generation script.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 27, 2026, 01:28 PM
Security Audit — agent-trust-hub — textbook-to-presentation-generator