presentation-creation
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill transforms raw, untrusted content like outlines and technical documents into presentation slide decks.
- Ingestion points: Source material is gathered from external documents, meeting notes, or data provided by the user (Workflow Step 1).
- Boundary markers: The skill lacks explicit instructions or delimiters that would direct the agent to ignore potentially malicious instructions hidden within the source material.
- Capability inventory: The skill generates interpretable content, including reveal.js HTML files and Python scripts using the python-pptx library (Workflow Step 5).
- Sanitization: There is no evidence of sanitization or validation protocols to filter input data before it is interpolated into the final output formats.
Audit Metadata