frontend-slides
Pass
Audited by Gen Agent Trust Hub on Apr 11, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill interacts with the local operating system to open generated HTML files. It uses platform-specific openers: 'open' for macOS, 'xdg-open' for Linux, and 'start' for Windows in the 'Deliver' section of SKILL.md.
- [COMMAND_EXECUTION]: The conversion workflow invokes 'python3' to execute scripts for processing presentation files.
- [EXTERNAL_DOWNLOADS]: The skill recommends installing 'python-pptx', a common Python library, to facilitate the extraction of text and assets from PowerPoint documents.
- [PROMPT_INJECTION]: An indirect prompt injection surface is present in the document conversion workflow (SKILL.md, PPT / PPTX Conversion).
- Ingestion points: Untrusted content is ingested from '.ppt' or '.pptx' files provided by the user.
- Boundary markers: There are no explicit instructions to use delimiters or to disregard potential instructions embedded within the slide content.
- Capability inventory: The skill can perform local file writes and execute shell commands through the 'Deliver' and 'Conversion' logic.
- Sanitization: The skill lacks explicit sanitization or validation of the text extracted from the PowerPoint files before it is processed by the agent to build the presentation.
Audit Metadata