frontend-slides
Pass
Audited by Gen Agent Trust Hub on Jun 22, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes platform-specific shell commands such as 'open', 'xdg-open', and 'start' to open generated HTML files in the user's default browser. This is a standard and expected functional feature for the stated purpose of creating presentations.
- [EXTERNAL_DOWNLOADS]: The skill references the use of 'python-pptx', a well-known and widely used Python library for document processing, to facilitate the conversion of PowerPoint files.
- [DATA_EXPOSURE]: The skill's primary function involves reading user-provided content and local presentation files (.ppt, .pptx) for extraction and conversion purposes. This behavior is documented and necessary for the tool's operation.
- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it processes external data from user notes and converted PowerPoint documents.
- Ingestion points: Ingests user-provided text, notes, and content from .ppt/.pptx files during the 'Discover Content' and 'PPT / PPTX Conversion' steps.
- Boundary markers: No explicit delimiters or instructions are provided to the agent to distinguish between extracted content and its own instructions.
- Capability inventory: The skill has the capability to write HTML files to the filesystem, execute python3 scripts, and run shell commands to open files.
- Sanitization: The instructions do not specify sanitization or escaping of extracted content before it is interpolated into the generated HTML presentation code.
Audit Metadata