pptx
Pass
Audited by Gen Agent Trust Hub on Mar 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses Python scripts located in the
gateway/tools/directory (e.g.,unpack.py,pack.py,clean.py,thumbnail.py) to manipulate and validate OOXML PowerPoint structures. These tools are used for the primary task of file editing and validation. - [PROMPT_INJECTION]: The skill exhibits vulnerability to indirect prompt injection by processing external data from .pptx files.
- Ingestion points: Reads content and metadata from user-provided .pptx files using tools like
markitdown(SKILL.md). - Boundary markers: No explicit delimiters or instructions to ignore embedded commands are used when passing extracted content to sub-agents.
- Capability inventory: Capability to execute local Python scripts, modify the file system, and delegate tasks to sub-agents (SKILL.md).
- Sanitization: No specific sanitization or filtering of extracted text is mentioned before it is processed by the AI.
Audit Metadata