pptx
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Indirect prompt injection surface identified.\n
- Ingestion points: Functions extract_content, create_presentation, add_image_slide, and markdown_to_presentation process external files or Markdown strings.\n
- Boundary markers: The skill does not implement delimiters or ignore-instructions logic for the content it processes.\n
- Capability inventory: The skill performs file read and write operations using the python-pptx library.\n
- Sanitization: There is no sanitization or validation of the input content before it is processed by the agent or written to files.\n- [SAFE]: The skill uses the legitimate and well-known python-pptx library for its primary operations.
Audit Metadata