office-pptx
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection through the processing of .pptx files.\n
- Ingestion points: Content is read from PowerPoint slides using the python-pptx library and an external check_office.py script.\n
- Boundary markers: There are no instructions for the agent to treat extracted slide text as untrusted data or to use delimiters.\n
- Capability inventory: The skill has the ability to write to the file system (presentation.save) and execute shell commands via the LibreOffice CLI.\n
- Sanitization: The instructions do not include steps for sanitizing or validating text extracted from presentations before the agent processes it.\n- [COMMAND_EXECUTION]: The skill uses a bundled LibreOffice Kit to execute shell commands for document processing.\n
- Evidence: It invokes a Node.js runtime and a CLI tool to perform render and convert operations on document files.
Audit Metadata