slide-generation
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests external JSON data to generate slide content, providing an entry point for indirect prompt injection.
- Ingestion points: Data is loaded from a JSON file in the scripts/slides.py script.
- Boundary markers: The script does not utilize delimiters or specific instructions to prevent the processing of instructions embedded in the input data.
- Capability inventory: The script has the ability to write files to the system but lacks network or administrative capabilities.
- Sanitization: There is no filtering or escaping of the input text before it is written to PPTX or Markdown files.
Audit Metadata