document-pptx
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external PowerPoint (.pptx) files, creating a surface for untrusted instructions to influence agent behavior.
- Ingestion points: Documented in
scripts/pptx_inventory.py,scripts/pptx_extract_notes.py, andreferences/extraction-stack.md. - Boundary markers: The provided extraction scripts do not implement delimiters or safety warnings to distinguish between content and instructions.
- Capability inventory: The skill has access to Bash execution and file writing, and provides templates that use Python's
subprocessfor system calls. - Sanitization: No sanitization is performed on the text extracted from slide components.
- [COMMAND_EXECUTION]: The skill includes code templates that use the
subprocessmodule to call system utilities for file conversion. - Evidence: Found in
assets/pitch-deck.md(callingunoconv) andreferences/pptx-speaker-notes-delivery.md(suggestinglibreoffice). - [DYNAMIC_EXECUTION]: The skill provides Python scripts and templates that are intended to be executed at runtime to generate or modify presentation files.
- Evidence: Python logic in
assets/pitch-deck.mdandassets/quarterly-review.mddemonstrates runtime slide assembly and data processing.
Audit Metadata