document-pptx
Pass
Audited by Gen Agent Trust Hub on Mar 13, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill provides functionality to extract text and table content from existing PowerPoint (.pptx) files, which creates a surface for indirect prompt injection. Malicious instructions embedded within slides could potentially override agent behavior if the extracted text is processed without sanitization.
- Ingestion points: Slide text extraction in SKILL.md via
Presentation('existing.pptx'). - Boundary markers: None present in the provided code snippets to distinguish between slide content and system instructions.
- Capability inventory: The skill can create and modify files, insert images, and generate charts.
- Sanitization: No sanitization or validation of extracted text is described in the extraction examples.
- [COMMAND_EXECUTION]: The skill contains Python and Node.js code snippets for file system interaction and document generation. These operations are limited to creating, saving, and reading local PowerPoint files, which is consistent with the skill's stated purpose.
Audit Metadata